Keiichi Tokuda

According to our database, Keiichi Tokuda authored at least 273 papers between 1990 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

LIMMITS'24: Multi-Speaker, Multi-Lingual Indic TTS with Voice Cloning.

Abhayjeet Singh, Amala Nagireddi, Deekshitha G, Jesuraja Bandekar, Roopa R., Sandhya Badiger, Sathvik Udupa, Prasanta Kumar Ghosh, Hema A. Murthy, Pranaw Kumar, Keiichi Tokuda, Mark Hasegawa-Johnson, Philipp Olbrich

Proceedings of the IEEE International Conference on Acoustics, 2024

PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model.

Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation.

Miku Nishihara, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

CoRR, 2023

SPTK4: An Open-Source Software Toolkit for Speech Signal Processing.

Takenori Yoshimura, Takato Fujimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the 12th ISCA Speech Synthesis Workshop, 2023

Embedding a Differentiable Mel-Cepstral Synthesis Filter to a Neural Speech Synthesis System.

Takenori Yoshimura, Shinji Takaki, Kazuhiro Nakamura, Keiichiro Oura, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2023

Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech.

Abhayjeet Singh, Amala Nagireddi, Deekshitha G, Jesuraja Bandekar, Roopa R., Sandhya Badiger, Sathvik Udupa, Prasanta Kumar Ghosh, Hema A. Murthy, Heiga Zen, Pranaw Kumar, Kamal Kant, Amol Bole, Bira Chandra Singh, Keiichi Tokuda, Mark Hasegawa-Johnson, Philipp Olbrich

Proceedings of the IEEE International Conference on Acoustics, 2023

Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism.

Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue.

Kentaro Mitsui, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Autoregressive Variational Autoencoder with a Hidden Semi-Markov Model-Based Structured Attention for Speech Synthesis.

Takato Fujimoto, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System.

Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

IEEE ACM Trans. Audio Speech Lang. Process., 2021

PeriodNet: A Non-Autoregressive Raw Waveform Generative Model With a Structure Separating Periodic and Aperiodic Components.

Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

IEEE Access, 2021

Periodnet: A Non-Autoregressive Waveform Generation Model with a Structure Separating Periodic and Aperiodic Components.

Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural F₀ Model for Statistical Parametric Speech Synthesis.

Xin Wang, Shinji Takaki, Junichi Yamagishi, Simon King, Keiichi Tokuda

IEEE ACM Trans. Audio Speech Lang. Process., 2020

Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis.

Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks.

Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Semi-Supervised Learning Based on Hierarchical Generative Models for End-to-End Speech Synthesis.

Takato Fujimoto, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Singing voice synthesis based on convolutional neural networks.

Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

CoRR, 2019

Low computational cost speech synthesis based on deep neural networks using hidden semi-Markov model structures.

Motoki Shimada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 10th ISCA Speech Synthesis Workshop, 2019

Deep neural network based real-time speech vocoder with periodic and aperiodic inputs.

Keiichiro Oura, Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 10th ISCA Speech Synthesis Workshop, 2019

Impacts of input linguistic feature representation on Japanese end-to-end speech synthesis.

Takato Fujimoto, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 10th ISCA Speech Synthesis Workshop, 2019

Statistical Approach to Speech Synthesis: Past, Present and Future.

Keiichi Tokuda

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Speaker-dependent Wavenet-based Delay-free Adpcm Speech Coding.

Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2019

Singing Voice Synthesis Based on Generative Adversarial Networks.

Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis.

Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

IEEE ACM Trans. Audio Speech Lang. Process., 2018

WaveNet-Based Zero-Delay Lossless Speech Coding.

Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Statistical Voice Conversion Based on Wavenet.

Jumpei Niwa, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Image Recognition Based on Separable Lattice Hmms Using a Deep Neural Network for Output Probability Distributions.

Eiji Ichikawa, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

The NITech text-to-speech system for the Blizzard Challenge 2018.

Kei Sawada, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2018, Hyderabad, India, September 8, 2018, 2018

Discriminative Feature Extraction Based on Sequential Variational Autoencoder for Speaker Recognition.

Takenori Yoshimura, Natsumi Koike, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Singing Voice Conversion Using Posted Waveform Data on Music Social Media.

Koki Senda, Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks Using Hidden Semi-Markov Model Structures.

Kento Nakao, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Image Recognition Based on Convolutional Neural Networks Using Features Generated from Separable Lattice Hidden Markov Models.

Takayuki Kasugai, Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Recent Development of the DNN-based Singing Voice Synthesis System - Sinsy.

Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Speech Synthesis Using WaveNet Vocoder Based on Periodic/Aperiodic Decomposition.

Takato Fujimoto, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

2017

Simultaneous Optimization of Multiple Tree-Based Factor Analyzed HMM for Speech Synthesis.

Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

IEEE ACM Trans. Audio Speech Lang. Process., 2017

Articulatory Text-to-Speech Synthesis Using the Digital Waveguide Mesh Driven by a Deep Neural Network.

Amelia Jane Gully, Takenori Yoshimura, Damian T. Murphy, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Image recognition based on discriminative models using features generated from separable lattice HMMS.

Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

The NITech text-to-speech system for the Blizzard Challenge 2017.

Kei Sawada, Kei Hashimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2017, Stockholm, Sweden, August 25, 2017, 2017

The blizzard machine learning challenge 2017.

Kei Sawada, Keiichi Tokuda, Simon King, Alan W. Black

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

Generalization of Thai tone contour in HMM-based speech synthesis.

Anocha Rugchatjaroen, Sittipong Saychum, Keiichiro Oura, Keiichi Tokuda

Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017

User Generated Dialogue Systems: uDialogue.

Keiichi Tokuda, Akinobu Lee, Yoshihiko Nankaku, Keiichiro Oura, Kei Hashimoto, Daisuke Yamamoto, Ichi Takumi, Takahiro Uchiya, Shuhei Tsutsumi, Steve Renals, Junichi Yamagishi

Proceedings of the Human-Harmonized Information Technology, Volume 2, 2017

2016

A Bayesian Approach to Image Recognition Based on Separable Lattice Hidden Markov Models.

Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2016

Temporal modeling in neural network based statistical parametric speech synthesis.

Keiichi Tokuda, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku

Proceedings of the 9th ISCA Speech Synthesis Workshop, 2016

A Hierarchical Predictor of Synthetic Speech Naturalness Using Neural Networks.

Takenori Yoshimura, Gustav Eje Henter, Oliver Watts, Mirjam Wester, Junichi Yamagishi, Keiichi Tokuda

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Singing Voice Synthesis Based on Deep Neural Networks.

Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Voice Conversion Based on Trajectory Model Training of Neural Networks Considering Global Variance.

Naoki Hosaka, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Redefining the Linguistic Context Feature Set for HMM and DNN TTS Through Position and Parsing.

Rasmus Dall, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Directly modeling voiced and unvoiced components in speech waveforms by neural networks.

Keiichi Tokuda, Heiga Zen

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Trajectory training considering global variance for speech synthesis based on neural networks.

Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

The NITech text-to-speech system for the Blizzard Challenge 2016.

Kei Sawada, Chiaki Asai, Kei Hashimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2016, Cuppertino, CA, USA, September 16, 2016, 2016

2015

Using speaker adaptive training to realize Mandarin-Tibetan cross-lingual speech synthesis.

Hongwu Yang, Keiichiro Oura, Haiyan Wang, Zhenye Gan, Keiichi Tokuda

Multim. Tools Appl., 2015

Simultaneous optimization of multiple tree structures for factor analyzed HMM-based speech synthesis.

Takenori Yoshimura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis.

Keiichi Tokuda, Heiga Zen

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

The effect of neural networks in statistical parametric speech synthesis.

Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

The NITECH HMM-based text-to-speech system for the Blizzard Challenge 2015.

Kei Sawada, Kei Hashimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2015, 2015

The Blizzard Challenge 2015.

Kishore Prahallad, Anandaswarup Vadapalli, Sai Krishna Rallabandi, Santosh Kesiraju, Hema A. Murthy, T. Nagarajan, Bira Chandra Singh, T. Sajani, K. Sreenivasa Rao, Suryakanth V. Gangashetty, Simon King, Keiichi Tokuda, Alan W. Black

Proceedings of the Blizzard Challenge 2015, 2015

2014

Introduction to the Issue on Statistical Parametric Speech Synthesis.

Jianhua Tao, Keikichi Hirose, Keiichi Tokuda, Alan W. Black, Simon King

IEEE J. Sel. Top. Signal Process., 2014

Contextual Additive Structure for HMM-Based Speech Synthesis.

Shinji Takaki, Yoshihiko Nankaku, Keiichi Tokuda

IEEE J. Sel. Top. Signal Process., 2014

Image Recognition Based on Separable Lattice Trajectory 2-D HMMs.

Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2014

Integration of Spectral Feature Extraction and Modeling for HMM-Based Speech Synthesis.

Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2014

A mel-cepstral analysis technique restoring high frequency components from low-sampling-rate speech.

Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Integration of speaker and pitch adaptive training for HMM-based singing voice synthesis.

Kanako Shirota, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2014

HMM-Based singing voice synthesis and its application to Japanese and English.

Kazuhiro Nakamura, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2014

Voice interaction system with 3D-CG virtual agent for stand-alone smartphones.

Daisuke Yamamoto, Keiichiro Oura, Ryota Nishimura, Takahiro Uchiya, Akinobu Lee, Ichi Takumi, Keiichi Tokuda

Proceedings of the second international conference on Human-agent interaction, 2014

Overview of NITECH HMM-based text-to-speech system for Blizzard Challenge 2014.

Kei Sawada, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2014, Singapore, Singapore, September 19, 2014, 2014

The Blizzard Challenge 2014.

Kishore Prahallad, Anandaswarup Vadapalli, Santosh Kesiraju, Hema A. Murthy, Swaran Lata, T. Nagarajan, S. R. Mahadeva Prasanna, Hemant A. Patil, Anil Kumar Sao, Simon King, Alan W. Black, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2014, Singapore, Singapore, September 19, 2014, 2014

2013

Speech Synthesis Based on Hidden Markov Models.

Keiichi Tokuda, Yoshihiko Nankaku, Tomoki Toda, Heiga Zen, Junichi Yamagishi, Keiichiro Oura

Proc. IEEE, 2013

A Bayesian Framework Using Multiple Model Structures for Speech Recognition.

Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2013

Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis.

John Dines, Hui Liang, Lakshmi Saheer, Matthew Gibson, William Byrne, Keiichiro Oura, Keiichi Tokuda, Junichi Yamagishi, Simon King, Mirjam Wester, Teemu Hirsimäki, Reima Karhila, Mikko Kurimo

Comput. Speech Lang., 2013

Cross-lingual speaker adaptation based on factor analysis using bilingual speech data for HMM-based speech synthesis.

Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Eighth ISCA Tutorial and Research Workshop on Speech Synthesis, 2013

Contextual partial additive structure for HMM-based speech synthesis.

Shinji Takaki, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2013

Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis.

Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2013

Separable lattice 2-D HMMS introducing state duration control for recognition of images with various variations.

Takaya Makino, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2013

Mmdagent - A fully open-source toolkit for voice interaction systems.

Akinobu Lee, Keiichiro Oura, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2013

Overview of NITECH HMM-based speech synthesis system for Blizzard Challenge 2013.

Shinji Takaki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2013, 2013

Realizing Tibetan speech synthesis by speaker adaptive training.

Hongwu Yang, Keiichiro Oura, Zhenye Gan, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2013

Image recognition based on hidden Markov eigen-image models using variational Bayesian method.

Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2013

2012

Product of Experts for Statistical Parametric Speech Synthesis.

Heiga Zen, Mark J. F. Gales, Yoshihiko Nankaku, Keiichi Tokuda

IEEE Trans. Speech Audio Process., 2012

Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping.

Keiichiro Oura, Junichi Yamagishi, Mirjam Wester, Simon King, Keiichi Tokuda

Speech Commun., 2012

Impacts of machine translation and speech synthesis on speech-to-speech translation.

Kei Hashimoto, Junichi Yamagishi, William Byrne, Simon King, Keiichi Tokuda

Speech Commun., 2012

An Extension of Separable Lattice 2-D HMMs for Rotational Data Variations.

Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2012

Cross-lingual Speaker Adaptation for HMM-based Speech Synthesis based on Perceptual Characteristics and Speaker Interpolation.

Viviane de Franca Oliveira, Sayaka Shiota, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

A Bayesian Approach to Speaker Recognition Based on GMMs Using Multiple Model Structures.

Takafumi Hattori, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

A model structure integration based on a Bayesian framework for speech recognition.

Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Face recognition based on separable lattice 2-D HMMS using variational bayesian method.

Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Pitch adaptive training for hmm-based singing voice synthesis.

Keiichiro Oura, Ayami Mase, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Face recognition based on extended separable lattice 2-D HMMS.

Keisuke Kumaki, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2012.

Shinji Takaki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2012, Portland, OR, USA, September 14, 2012, 2012

2011

Continuous Stochastic Feature Mapping Based on Trajectory HMMs.

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

IEEE Trans. Speech Audio Process., 2011

Bayesian Context Clustering Using Cross Validation for Speech Recognition.

Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2011

Estimation of Perceptual Spaces for Speaker Identities Based on the Cross-Lingual Discrimination Task.

Minoru Tsuzaki, Keiichi Tokuda, Hisashi Kawai, Jinfu Ni

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

GMM-Based Missing-Feature Reconstruction on Multi-Frame Windows.

Ulpu Remes, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

A Bayesian Approach to Voice Conversion Based on GMMs Using Multiple Model Structures.

Lei Li, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Large-Scale Subjective Evaluations of Speech Rate Control Methods for HMM-Based Speech Synthesizers.

Tsuneo Kato, Makoto Yamada, Nobuyuki Nishizawa, Keiichiro Oura, Keiichi Tokuda

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Multi-Speaker Modeling with Shared Prior Distributions and Model Structures for Bayesian Speech Synthesis.

Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Estimation of Window Coefficients for Dynamic Feature Extraction for HMM-Based Speech Synthesis.

Ling-Hui Chen, Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Zhen-Hua Ling, Li-Rong Dai

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis.

Shinji Takaki, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2011

Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis.

Shifeng Pan, Yoshihiko Nankaku, Keiichi Tokuda, Jianhua Tao

Proceedings of the IEEE International Conference on Acoustics, 2011

An analysis of machine translation and speech synthesis in speech-to-speech translation system.

Kei Hashimoto, Junichi Yamagishi, William J. Byrne, Simon King, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2011

Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011.

Kei Hashimoto, Shinji Takaki, Keiichiro Oura, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2011, Turin, Italy, September 2, 2011, 2011

2010

Thousands of Voices for HMM-Based Speech Synthesis-Analysis and Application of TTS Systems Built on Various ASR Corpora.

Junichi Yamagishi, Bela Usabaev, Simon King, Oliver Watts, John Dines, Jilei Tian, Yong Guan, Rile Hu, Keiichiro Oura, Yi-Jian Wu, Keiichi Tokuda, Reima Karhila, Mikko Kurimo

IEEE Trans. Speech Audio Process., 2010

A Covariance-Tying Technique for HMM-Based Speech Synthesis.

Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2010

Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project.

Mirjam Wester, John Dines, Matthew Gibson, Hui Liang, Yi-Jian Wu, Lakshmi Saheer, Simon King, Keiichiro Oura, Philip N. Garner, William Byrne, Yong Guan, Teemu Hirsimäki, Reima Karhila, Mikko Kurimo, Matt Shannon, Sayaka Shiota, Jilei Tian, Keiichi Tokuda, Junichi Yamagishi

Proceedings of the Seventh ISCA Tutorial and Research Workshop on Speech Synthesis, 2010

Spectral modeling with contextual additive structure for HMM-based speech synthesis.

Shinji Takaki, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Seventh ISCA Tutorial and Research Workshop on Speech Synthesis, 2010

Recent development of the HMM-based singing voice synthesis system - Sinsy.

Keiichiro Oura, Ayami Mase, Tomohiko Yamada, Satoru Muto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Seventh ISCA Tutorial and Research Workshop on Speech Synthesis, 2010

Bayesian speech synthesis framework integrating training and synthesis processes.

Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Seventh ISCA Tutorial and Research Workshop on Speech Synthesis, 2010

Voice activity detection based on conditional random fields using multiple features.

Akira Saito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

HMM-based singing voice synthesis system using pitch-shifted pseudo training data.

Ayami Mase, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Speaker adaptation based on nonlinear spectral transform for speech recognition.

Toyohiro Hayashi, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Statistical parametric speech synthesis based on product of experts.

Heiga Zen, Mark J. F. Gales, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2010

Face recognition based on separable lattice 2-D HMM with state duration modeling.

Yoshiaki Takahashi, Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2010

Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis.

Keiichiro Oura, Keiichi Tokuda, Junichi Yamagishi, Simon King, Mirjam Wester

Proceedings of the IEEE International Conference on Acoustics, 2010

Factor analyzed voice models for HMM-based speech synthesis.

Kyosuke Kazumi, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2010

A Deterministic Annealing-Based Training Algorithm For Statistical Machine Translation Models.

Pascual Martínez-Gómez, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda, Germán Sanchis-Trilles

Proceedings of the 14th Annual conference of the European Association for Machine Translation, 2010

NICT Blizzard Challenge 2010 Entry.

Yoshinori Shiga, Tomoki Toda, Shinsuke Sakai, Jinfu Ni, Hisashi Kawai, Keiichi Tokuda, Minoru Tsuzaki, Satoshi Nakamura

Proceedings of the Blizzard Challenge 2010, Kansai Science City, Japan, September 25, 2010, 2010

Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2010.

Keiichiro Oura, Kei Hashimoto, Sayaka Shiota, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2010, Kansai Science City, Japan, September 25, 2010, 2010

2009

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis.

Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhen-Hua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, Steve Renals

IEEE Trans. Speech Audio Process., 2009

Statistical parametric speech synthesis.

Heiga Zen, Keiichi Tokuda, Alan W. Black

Speech Commun., 2009

A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation.

Kei Hashimoto, Hirofumi Yamamoto, Hideo Okuma, Eiichiro Sumita, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2009

Reordering Model Using Syntactic Information of a Source Tree for Statistical Machine Translation.

Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro Sumita, Keiichi Tokuda

Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation, 2009

Thousands of voices for HMM-based speech synthesis.

Junichi Yamagishi, Bela Usabaev, Simon King, Oliver Watts, John Dines, Jilei Tian, Rile Hu, Yong Guan, Keiichiro Oura, Keiichi Tokuda, Reima Karhila, Mikko Kurimo

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

An improved minimum generation error based model adaptation for HMM-based speech synthesis.

Yi-Jian Wu, Long Qin, Keiichi Tokuda

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis.

Yi-Jian Wu, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Deterministic annealing based training algorithm for Bayesian speech recognition.

Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems.

Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis.

Ranniery Maia, Tomoki Toda, Keiichi Tokuda, Shinsuke Sakai, Satoshi Nakamura

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

A Bayesian approach to Hidden Semi-Markov Model based speech synthesis.

Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Stereo-based stochastic noise compensation based on trajectory GMMS.

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2009

Voice conversion based on simultaneous modelling of spectrum and F0.

Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2009

Minimum generation error training by using original spectrum as reference for log spectral distortion measure.

Yi-Jian Wu, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2009

Full covariance state duration modeling for HMM-based speech synthesis.

Heng Lu, Yi-Jian Wu, Keiichi Tokuda, Li-Rong Dai, Ren-Hua Wang

Proceedings of the IEEE International Conference on Acoustics, 2009

A Bayesian approach to HMM-based speech synthesis.

Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Takashi Masuko, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2009

Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2009.

Keiichiro Oura, Yi-Jian Wu, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2009, Edinburgh, Scotland, UK, September 4, 2009, 2009

The NICT Entry for the Blizzard Challenge 2009: an Enhanced HMM-based Speech Synthesis System with Trajectory Training considering Global Variance and State-Dependent Mixed Excitation.

Ranniery Maia, Tomoki Toda, Shinsuke Sakai, Yoshinori Shiga, Jinfu Ni, Hisashi Kawai, Keiichi Tokuda, Minoru Tsuzaki, Satoshi Nakamura

Proceedings of the Blizzard Challenge 2009, Edinburgh, Scotland, UK, September 4, 2009, 2009

2008

Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model.

Tomoki Toda, Alan W. Black, Keiichi Tokuda

Speech Commun., 2008

The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006.

Heiga Zen, Tomoki Toda, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2008

A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System.

Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2008

Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis.

Yi-Jian Wu, Simon King, Keiichi Tokuda

Proceedings of the 6th International Symposium on Chinese Spoken Language Processing, 2008

Simultaneous Acoustic, Prosodic, and Phrasing Model Training for TTs Conversion Systems.

Keiichiro Oura, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda, Ranniery Maia, Shinsuke Sakai, Satoshi Nakamura

Proceedings of the 6th International Symposium on Chinese Spoken Language Processing, 2008

Probabilistic feature mapping based on trajectory HMMs.

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Simultaneous conversion of duration and spectrum based on statistical models including time-sequence matching.

Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Probabilistic answer selection based on conditional random fields for spoken dialog system.

Yoshitaka Yoshimi, Ryota Kakitsuba, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis.

Yi-Jian Wu, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Acoustic modeling based on model structure annealing for speech recognition.

Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Unsupervised adaptation for HMM-based speech synthesis.

Simon King, Keiichi Tokuda, Heiga Zen, Junichi Yamagishi

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Speaker recognition based on variational Bayesian method.

Tatsuya Ito, Kei Hashimoto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition.

Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS 2007" for the Blizzard Challenge 2007.

Junichi Yamagishi, Takashi Nose, Heiga Zen, Tomoki Toda, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2008

Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM.

Tomoki Toda, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2008

Acoustic modeling with contextual additive structure for HMM-based speech recognition.

Yoshihiko Nankaku, Kazuhiro Nakamura, Heiga Zen, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2008

On the state definition for a trainable excitation model in HMM-based speech synthesis.

Ranniery Maia, Tomoki Toda, Keiichi Tokuda, Shinichi Sakai, Shun Nakamura

Proceedings of the IEEE International Conference on Acoustics, 2008

The HTS-2008 System: Yet Another Evaluation of the Speaker-Adaptive HMM-based Speech Synthesis System in The 2008 Blizzard Challenge.

Junichi Yamagishi, Heiga Zen, Yi-Jian Wu, Tomoki Toda, Keiichi Tokuda

Proceedings of the Blizzard Challenge 2008, 2008

The NICT/ATR speech synthesis system for the Blizzard Challenge 2008.

Ranniery Maia, Jinfu Ni, Shinsuke Sakai, Tomoki Toda, Keiichi Tokuda, Tohru Shimizu, Satoshi Nakamura

Proceedings of the Blizzard Challenge 2008, 2008

2007

Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory.

Tomoki Toda, Alan W. Black, Keiichi Tokuda

IEEE Trans. Speech Audio Process., 2007

Vector quantization of mel-cepstral coefficients using distortion measure for spectral analysis.

Toru Takahashi, Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura

Syst. Comput. Jpn., 2007

Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005.

Heiga Zen, Tomoki Toda, Masaru Nakamura, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2007

A Hidden Semi-Markov Model-Based Speech Synthesis System.

Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

IEICE Trans. Inf. Syst., 2007

State Duration Modeling for HMM-Based Speech Synthesis.

Heiga Zen, Takashi Masuko, Keiichi Tokuda, Takayoshi Yoshimura, Takao Kobayashi, Tadashi Kitamura

IEICE Trans. Inf. Syst., 2007

A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis.

Tomoki Toda, Keiichi Tokuda

IEICE Trans. Inf. Syst., 2007

Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences.

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura

Comput. Speech Lang., 2007

The HMM-based speech synthesis system (HTS) version 2.0.

Heiga Zen, Takashi Nose, Junichi Yamagishi, Shinji Sako, Takashi Masuko, Alan W. Black, Keiichi Tokuda

Proceedings of the Sixth ISCA Workshop on Speech Synthesis, 2007

Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV.

Junichi Yamagishi, Takao Kobayashi, Steve Renals, Simon King, Heiga Zen, Tomoki Toda, Keiichi Tokuda

Proceedings of the Sixth ISCA Workshop on Speech Synthesis, 2007

Communicative speech synthesis with XIMERA: a first step.

Shinsuke Sakai, Jinfu Ni, Ranniery Maia, Keiichi Tokuda, Minoru Tsuzaki, Tomoki Toda, Hisashi Kawai, Satoshi Nakamura

Proceedings of the Sixth ISCA Workshop on Speech Synthesis, 2007

Spectral conversion based on statistical models including time-sequence matching.

Yoshihiko Nankaku, Kenichi Nakamura, Tomoki Toda, Keiichi Tokuda

Proceedings of the Sixth ISCA Workshop on Speech Synthesis, 2007

An excitation model for HMM-based speech synthesis based on residual modeling.

Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Sixth ISCA Workshop on Speech Synthesis, 2007

Model-space MLLR for trajectory HMMs.

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

A trainable excitation model for HMM-based speech synthesis.

Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Face Recognition using Hidden Markov Eigenface Models.

Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the IEEE International Conference on Acoustics, 2007

Speaker-independent HMM-based speech synthesis system - HTS-2007 system for the Blizzard Challenge 2007.

Junichi Yamagishi, Heiga Zen, Tomoki Toda, Keiichi Tokuda

Proceedings of the Evaluation of text-to-speech systems: Blizzard Challenge 2007, 2007

ATRECSS - ATR English speech corpus for speech synthesis.

Jinfu Ni, Toshio Hirai, Hisashi Kawai, Tomoki Toda, Keiichi Tokuda, Minoru Tsuzaki, Shinsuke Sakai, Ranniery Maia, Satoshi Nakamura

Proceedings of the Evaluation of text-to-speech systems: Blizzard Challenge 2007, 2007

2006

Very low bit rate speech coding based on HMM with speaker adaptation.

Takashi Masuko, Takao Kobayashi, Keiichi Tokuda

Syst. Comput. Jpn., 2006

An HMM-Based Approach to Flexible Speech Synthesis.

Keiichi Tokuda

Proceedings of the Chinese Spoken Language Processing, 5th International Symposium, 2006

Speaker adaptation of trajectory HMMs using feature-space MLLR.

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Voice conversion based on mixtures of factor analyzers.

Yosuke Uto, Yoshihiko Nankaku, Tomoki Toda, Akinobu Lee, Keiichi Tokuda

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

An HMM-based singing voice synthesis system.

Keijiro Saino, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Reducing computation on parallel decoding using frame-wise confidence scores.

Tomohiro Hakamata, Akinobu Lee, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Estimating Trajectory Hmm Parameters Using Monte Carlo Em With Gibbs Sampler.

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Hidden Semi-Markov Model Based Speech Recognition System using Weighted Finite-State Transducer.

Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

On the Use of Phonetic Information for Mapping from Articulatory Movements to Vocal Tract Spectrum.

Kenichi Nakamura, Tomoki Toda, Yoshihiko Nankaku, Keiichi Tokuda

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Face Recognition Based on Separable Lattice HMMS.

Daisuke Kurata, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Zoubin Ghahramani

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Developing a Test Bed of English Text-to-Speech System XIMERA for the Blizzard Challenge 2006.

Tomoki Toda, Hisashi Kawai, Toshio Hirai, Jinfu Ni, Nobuyuki Nishizawa, Junichi Yamagishi, Minoru Tsuzaki, Keiichi Tokuda, Satoshi Nakamura

Proceedings of the Blizzard Challenge 2006, Pittsburgh, PA, USA, September 16, 2006, 2006

2005

Simultaneous clustering of phonetic context, dimension, and state position for acoustic modeling using decision trees.

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura

Syst. Comput. Jpn., 2005

Incorporating a mixed excitation model and postfilter into HMM-based text-to-speech synthesis.

Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Syst. Comput. Jpn., 2005

Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification.

Hiroyoshi Yamamoto, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

IEICE Trans. Inf. Syst., 2005

Continuous Speech Recognition Based on General Factor Dependent Acoustic Models.

Hiroyuki Suzuki, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

IEICE Trans. Inf. Syst., 2005

Applying Sparse KPCA for Feature Extraction in Speech Recognition.

Amaro A. de Lima, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Fernando Gil Resende

IEICE Trans. Inf. Syst., 2005

Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition.

Yohei Itaya, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

IEICE Trans. Inf. Syst., 2005

The blizzard challenge - 2005: evaluating corpus-based speech synthesis on common datasets.

Alan W. Black, Keiichi Tokuda

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

HMM-based european Portuguese TTS system.

Maria João Barros, Ranniery Maia, Keiichi Tokuda, Fernando Gil Resende, Diamantino Freitas

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Spectral Conversion Based on Maximum Likelihood Estimation Considering Global Variance of Converted Parameter.

Tomoki Toda, Alan W. Black, Keiichi Tokuda

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

Sparse KPCA for Feature Extraction in Speech Recognition.

Amaro A. de Lima, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Fernando Gil Resende

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

Minimum Classification Error Interactive Training for Speaker Identification.

Yusuke Kida, Hiroyoshi Yamamoto, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents.

Shinichi Kawamoto, Hiroshi Shimodaira, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katsunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Atsuhiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro, Shigeki Sagayama

Proceedings of the Life-like characters - tools, affective functions, and applications., 2004

Speaker adaptation of pitch and spectrum for HMM-based speech synthesis.

Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Syst. Comput. Jpn., 2004

On the Use of Kernel PCA for Feature Extraction in Speech Recognition.

Amaro A. de Lima, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

IEICE Trans. Inf. Syst., 2004

An introduction of trajectory model into HMM-based speech synthesis.

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the Fifth ISCA ITRW on Speech Synthesis, 2004

Mapping from articulatory movements to vocal tract spectrum with Gaussian mixture model for articulatory speech synthesis.

Tomoki Toda, Alan W. Black, Keiichi Tokuda

Proceedings of the Fifth ISCA ITRW on Speech Synthesis, 2004

XIMERA: a new TTS from ATR based on corpus-based technologies.

Hisashi Kawai, Tomoki Toda, Jinfu Ni, Minoru Tsuzaki, Keiichi Tokuda

Proceedings of the Fifth ISCA ITRW on Speech Synthesis, 2004

Hidden semi-Markov model based speech synthesis.

Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Constructing emotional speech synthesizers with limited speech database.

Heiga Zen, Tadashi Kitamura, Murtaza Bulut, Shrikanth S. Narayanan, Ryosuke Tsuzuki, Keiichi Tokuda

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Acoustic-to-articulatory inversion mapping with Gaussian mixture model.

Tomoki Toda, Alan W. Black, Keiichi Tokuda

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Decision-tree backing-off in HMM-based speech synthesis.

Shunsuke Kataoka, Nobuaki Mizutani, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Deterministic annealing EM algorithm in parameter estimation for acoustic model.

Yohei Itaya, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features.

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Parameter sharing and minimum classification error training of mixtures of factor analyzers for speaker identification.

Hiroyoshi Yamamoto, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003

A Training Method of Average Voice Model for HMM-Based Speech Synthesis.

Junichi Yamagishi, Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2003

Mixture Density Models Based on Mel-Cepstral Representation of Gaussian Process.

Toru Takahashi, Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2003

Decision tree-based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling.

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features.

Keiichi Tokuda, Heiga Zen, Tadashi Kitamura

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Towards the development of a brazilian portuguese text-to-speech system based on HMM.

Ranniery Maia, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Fernando Gil Vianna Resende Jr.

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

A training method for average voice model based on shared decision tree context clustering and speaker adaptive training.

Junichi Yamagishi, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

Speech recognition using voice-characteristic-dependent acoustic models.

Hiroyuki Suzuki, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

Improving the performance of HMM-based very low bit rate speech coding.

Takahiro Hoshiya, Shinji Sako, Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Pitch pattern generation using multispace probability distribution HMM.

Takashi Masuko, Keiichi Tokuda, Noboru Miyazaki, Takao Kobayashi

Syst. Comput. Jpn., 2002

Decision tree distribution tying based on a dimensional split technique.

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

A context clustering technique for average voice model in HMM-based speech synthesis.

Junichi Yamagishi, Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Eigenvoices for HMM-based speech synthesis.

Kengo Shichiri, Atsushi Sawabe, Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

A new algorithm for updating adaptive system.

Junibakti Sanubari, Keiichi Tokuda

Proceedings of the IEEE Asia Pacific Conference on Circuits and Systems 2002, 2002

2001

A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction.

Chiyomi Miyajima, Hideyuki Watanabe, Keiichi Tokuda, Tadashi Kitamura, Shigeru Katagiri

Speech Commun., 2001

Very low bit rate speech coding based on HMMs.

Jun Hiroi, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Syst. Comput. Jpn., 2001

Fast convergence transversal adaptive filtering algorithm for impulsive environment based on T distribution assumption.

Junibakti Sanubari, Keiichi Tokuda

Proceedings of the 2001 International Symposium on Circuits and Systems, 2001

Mixed excitation for HMM-based speech synthesis.

Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Text-to-speech synthesis with arbitrary speaker's voice from average voice.

Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

A robust speaker verification system against imposture using an HMM-based speech synthesis system.

Takayuki Satoh, Takashi Masuko, Takao Kobayashi, Keiichi Tokuda

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Minimum classification error training for speaker identification using Gaussian mixture models based on multi-space probability distribution.

Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR.

Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the IEEE International Conference on Acoustics, 2001

Speaker identification using Gaussian mixture models based on multi-space probability distribution.

Chiyomi Miyajima, Yosuke Hattori, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the IEEE International Conference on Acoustics, 2001

2000

RLS-type two-dimensional adaptive filter with a t-distribution assumption.

Junibakti Sanubari, Keiichi Tokuda

Signal Process., 2000

HMM-based text-to-audio-visual speech synthesis.

Shinji Sako, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Audio-visual speech recognition using MCE-based hmms and model-dependent stream weights.

Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Imposture using synthetic speech against speaker verification based on spectrum and pitch.

Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Normalized Training for HMM-Based Visual Speech Recognition.

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Takao Kobayashi

Proceedings of the 2000 International Conference on Image Processing, 2000

Speech parameter generation algorithms for HMM-based speech synthesis.

Keiichi Tokuda, Takayoshi Yoshimura, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the IEEE International Conference on Acoustics, 2000

Robust estimation of an AR multi-channel model by using t-distribution assumption.

Junibakti Sanubari, Keiichi Tokuda

Proceedings of the 10th European Signal Processing Conference, 2000

1999

A New Robust Two Dimensional Spectral Estimation Based on an AR Model Excited by a t Distribution Process and its QR-Decomposition Recursive Algorithm.

Junibakti Sanubari, Keiichi Tokuda

J. Circuits Syst. Comput., 1999

LMS-like two dimensional adaptive filter with t-distribution assumption and nonsymmetrical half-plane support.

Junibakti Sanubari, Keiichi Tokuda

Proceedings of the IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing (NSIP'99), 1999

Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis.

Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Intensity- and location-normalized training for HMM-based visual speech recognition.

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

On the security of HMM-based speaker verification systems against imposture using synthetic speech.

Takashi Masuko, Takafumi Hitotsumatsu, Keiichi Tokuda, Takao Kobayashi

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Location Normalization of HMM-Based Lip Reading: Experiments for the M2VTS Database.

Oscar Vanegas, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 1999 International Conference on Image Processing, 1999

Image Modeling Using Two Dimensional Exponential Systems.

Junibakti Sanubari, Keiichi Tokuda

Proceedings of the 1999 International Conference on Image Processing, 1999

Hidden Markov models based on multi-space probability distribution for pitch pattern modeling.

Keiichi Tokuda, Takashi Masuko, Noboru Miyazaki, Takao Kobayashi

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998

Robust recursive time series modeling based on an AR model excited by a t-distribution process.

Junibakti Sanubari, Keiichi Tokuda, Mahoki Onoda

IEEE Trans. Signal Process., 1998

Speaker adaptation for HMM-based speech synthesis system using MLLR.

Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the Third ESCA/COCOSDA Workshop on Speech Synthesis, 1998

Duration modeling for HMM-based speech synthesis.

Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

HMM-based visual speech recognition using intensity and location normalization.

Oscar Vanegas, Akiji Tanaka, Keiichi Tokuda, Tadashi Kitamura

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

A very low bit rate speech coder using HMM with speaker adaptation.

Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

A 16 kbit/s wideband CELP coder using MEL-generalized cepstral analysis and its subjective evaluation.

Kazuhito Koishida, Gou Hirabayashi, Keiichi Tokuda, Takao Kobayashi

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

A very low bit rate speech coder using HMM-based speech recognition/synthesis techniques.

Keiichi Tokuda, Takashi Masuko, Jun Hiroi, Takao Kobayashi, Tadashi Kitamura

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Text-to-visual speech synthesis based on parameter generation from HMM.

Takashi Masuko, Takao Kobayashi, Masatsune Tamura, Jun Masubuchi, Keiichi Tokuda

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

A wideband CELP speech coder at 16 kbit/s based on mel-generalized cepstral analysis.

Kazuhito Koishida, Gou Hirabayashi, Keiichi Tokuda, Takao Kobayashi

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Visual Speech Synthesis Based on Parameter Generation From HMM: Speech-Driven and Text-And-Speech-Driven Approaches.

Masatsune Tamura, Takashi Masuko, Takao Kobayashi, Keiichi Tokuda

Proceedings of the Auditory-Visual Speech Processing, 1998

1997

Speaker interpolation in HMM-based speech synthesis system.

Takayoshi Yoshimura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

HMM compensation for noisy speech recognition based on cepstral parameter generation.

Takao Kobayashi, Takashi Masuko, Keiichi Tokuda

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Voice characteristics conversion for HMM-based speech synthesis system.

Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

Efficient encoding of mel-generalized cepstrum for CELP coders.

Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1996

CELP coding system based on mel-generalized cepstral analysis.

Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Robust two dimensional spectral estimation based on AR model excited by a t-distribution process.

Junibakti Sanubari, Keiichi Tokuda, Mahoki Onoda

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

Speech synthesis using HMMs with dynamic features.

Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

1995

Adaptive cepstral analysis of speech.

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

IEEE Trans. Speech Audio Process., 1995

An algorithm for speech parameter generation from continuous mixture HMMs with dynamic features.

Keiichi Tokuda, Takashi Masuko, Tetsuya Yamada, Takao Kobayashi, Satoshi Imai

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

Speech parameter generation from HMM using dynamic features.

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 1995 International Conference on Acoustics, 1995

CELP coding based on mel-cepstral analysis.

Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

AR Spectrum Estimation Based on Wavelet Representation.

Fernando Gil Resende, Keiichi Tokuda, Mineo Kaneko

Proceedings of the 1994 IEEE International Symposium on Circuits and Systems, ISCAS 1994, London, England, UK, May 30, 1994

Mel-generalized cepstral analysis - a unified approach to speech spectral estimation.

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, Satoshi Imai

Proceedings of the 3rd International Conference on Spoken Language Processing, 1994

Speech coding based on adaptive MEL-cepstral analysis for noisy channels.

Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 3rd International Conference on Spoken Language Processing, 1994

Speech coding based on adaptive mel-cepstral analysis.

Keiichi Tokuda, Hidetoshi Matsumura, Takao Kobayashi, Satoshi Imai

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

Robust recursive spectral estimation based on AR model excited by a t-distribution process.

Junibakti Sanubari, Keiichi Tokuda, Mahoki Onoda

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

1992

Spectral estimation based on AR-model excited by t-distribution process.

Junibakti Sanubari, Keiichi Tokuda, Mahoki Onoda

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

Design of stable two-dimensional IIR digital filters with arbitrary magnitude function.

Takao Kobayashi, Kazuyoshi Fukushi, Keiichi Tokuda, Satoshi Imai

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

An adaptive algorithm for mel-cepstral analysis of speech.

Toshiaki Fukada, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

1990

Generalized cepstral analysis of speech - unified approach to LPC and cepstral method.

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

Proceedings of the First International Conference on Spoken Language Processing, 1990

Adaptive filtering based on cepstral representation-adaptive cepstral analysis of speech.

Keiichi Tokuda, Takao Kobayashi, Shoji Shiomoto, Satoshi Imai

Proceedings of the 1990 International Conference on Acoustics, 1990