Takuya Higuchi

According to our database, Takuya Higuchi authored at least 38 papers between 2001 and 2024.

Collaborative distances:

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

2024

Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels.

Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Li-Wei Chen, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald

CoRR, 2024

Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models.

Li-Wei Chen, Takuya Higuchi, He Bai, Ahmed Hussen Abdelaziz, Alexander Rudnicky, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald, Zakaria Aldeneh

CoRR, 2024

Towards Automatic Assessment of Self-Supervised Speech Models using Rank.

Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi, Barry-John Theobald, Tatiana Likhomanenko

CoRR, 2024

Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations.

Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden

CoRR, 2024

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?

Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald

CoRR, 2024

ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models.

Jee-weon Jung, Wangyou Zhang, Jiatong Shi, Zakaria Aldeneh, Takuya Higuchi, Barry-John Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe

CoRR, 2024

Multichannel Voice Trigger Detection Based on Transform-Average-Concatenate.

Takuya Higuchi, Avamarie Brueggeman, Masood Delfarah, Stephen Shum

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Does Single-channel Speech Enhancement Improve Keyword Spotting Accuracy? A Case Study.

Avamarie Brueggeman, Takuya Higuchi, Masood Delfarah, Stephen Shum, Vineet Garg

CoRR, 2023

2022

Improving Voice Trigger Detection with Metric Learning.

Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed H. Tewfik

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

2021

Dynamic Curriculum Learning via Data Parameters for Noise Robust Keyword Spotting.

Takuya Higuchi, Shreyas Saxena, Mehrez Souden, Tien Dung Tran, Masood Delfarah, Chandra Dhir

Proceedings of the IEEE International Conference on Acoustics, 2021

Multi-Task Learning with Cross Attention for Keyword Spotting.

Takuya Higuchi, Anmol Gupta, Chandra Dhir

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2020

Stacked 1D Convolutional Networks for End-to-End Small Footprint Voice Trigger Detection.

Takuya Higuchi, Mohammad Ghasemzadeh, Kisun You, Chandra Dhir

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

2018

Nonnegative Matrix Factorization With Basis Clustering Using Cepstral Distance Regularization.

Hirokazu Kameoka, Takuya Higuchi, Mikihiro Tanaka, Li Li

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

Optimization of Speaker-Aware Multichannel Speech Extraction with ASR Criterion.

Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Takuya Higuchi, Tomohiro Nakatani, Jan Cernocký

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Frame-by-Frame Closed-Form Update for Mask-Based Adaptive MVDR Beamforming.

Takuya Higuchi, Keisuke Kinoshita, Nobutaka Ito, Shigeki Karita, Tomohiro Nakatani

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation.

Lukas Drude, Takuya Higuchi, Keisuke Kinoshita, Tomohiro Nakatani, Reinhold Haeb-Umbach

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Online MVDR Beamformer Based on Complex Gaussian Mixture Model With Spatial Prior for Noise Robust ASR.

Takuya Higuchi, Nobutaka Ito, Shoko Araki, Takuya Yoshioka, Marc Delcroix, Tomohiro Nakatani

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

Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures.

Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Takuya Higuchi, Atsunori Ogawa, Tomohiro Nakatani

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

Deep Clustering-Based Beamforming for Separation with Unknown Number of Sources.

Takuya Higuchi, Keisuke Kinoshita, Marc Delcroix, Katerina Zmolíková, Tomohiro Nakatani

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

Integrating DNN-based and spatial clustering-based mask estimation for robust MVDR beamforming.

Tomohiro Nakatani, Nobutaka Ito, Takuya Higuchi, Shoko Araki, Keisuke Kinoshita

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Deep mixture density network for statistical model-based feature enhancement.

Keisuke Kinoshita, Marc Delcroix, Atsunori Ogawa, Takuya Higuchi, Tomohiro Nakatani

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Unsupervised utterance-wise beamformer estimation with speech recognition-level criterion.

Takuya Higuchi, Takuya Yoshioka, Keisuke Kinoshita, Tomohiro Nakatani

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Online meeting recognition in noisy environments with time-frequency mask based MVDR beamforming.

Shoko Araki, Nobutaka Ito, Marc Delcroix, Atsunori Ogawa, Keisuke Kinoshita, Takuya Higuchi, Takuya Yoshioka, Dung T. Tran, Shigeki Karita, Tomohiro Nakatani

Proceedings of the Hands-free Speech Communications and Microphone Arrays, 2017

Learning speaker representation for neural network based multichannel speaker extraction.

Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Takuya Higuchi, Atsunori Ogawa, Tomohiro Nakatani

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

Adversarial training for data-driven speech enhancement without parallel corpus.

Takuya Higuchi, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani

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

Multichannel Speech Enhancement Approaches to DNN-Based Far-Field Speech Recognition.

Marc Delcroix, Takuya Yoshioka, Nobutaka Ito, Atsunori Ogawa, Keisuke Kinoshita, Masakiyo Fujimoto, Takuya Higuchi, Shoko Araki, Tomohiro Nakatani

Proceedings of the New Era for Robust Speech Recognition, Exploiting Deep Learning., 2017

2016

Sparseness-based multichannel nonnegative matrix factorization for blind source separation.

Takuya Higuchi, Takuya Yoshioka, Tomohiro Nakatani

Proceedings of the IEEE International Workshop on Acoustic Signal Enhancement, 2016

Semi-Supervised Joint Enhancement of Spectral and Cepstral Sequences of Noisy Speech.

Li Li, Hirokazu Kameoka, Takuya Higuchi, Hiroshi Saruwatari

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

Optimization of Speech Enhancement Front-End with Speech Recognition-Level Criterion.

Takuya Higuchi, Takuya Yoshioka, Tomohiro Nakatani

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

Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise.

Takuya Higuchi, Nobutaka Ito, Takuya Yoshioka, Tomohiro Nakatani

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Spatial correlation model based observation vector clustering and MVDR beamforming for meeting recognition.

Shoko Araki, Masahiro Okada, Takuya Higuchi, Atsunori Ogawa, Tomohiro Nakatani

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Unified approach for audio source separation with multichannel factorial HMM and DOA mixture model.

Takuya Higuchi, Hirokazu Kameoka

Proceedings of the 23rd European Signal Processing Conference, 2015

The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices.

Takuya Yoshioka, Nobutaka Ito, Marc Delcroix, Atsunori Ogawa, Keisuke Kinoshita, Masakiyo Fujimoto, Chengzhu Yu, Wojciech J. Fabian, Miquel Espi, Takuya Higuchi, Shoko Araki, Tomohiro Nakatani

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014

Joint audio source separation and dereverberation based on multichannel factorial hidden Markov model.

Takuya Higuchi, Hirokazu Kameoka

Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, 2014

A unified approach for underdetermined blind signal separation and source activity detection by multichannel factorial hidden Markov models.

Takuya Higuchi, Hirofumi Takeda, Tomohiko Nakamura, Hirokazu Kameoka

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

Underdetermined blind separation and tracking of moving sources based ONDOA-HMM.

Takuya Higuchi, Norihiro Takamune, Tomohiko Nakamura, Hirokazu Kameoka

Proceedings of the IEEE International Conference on Acoustics, 2014

Unified approach for underdetermined BSS, VAD, dereverberation and DOA estimation with multichannel factorial HMM.

Takuya Higuchi, Hirokazu Kameoka

Proceedings of the 2014 IEEE Global Conference on Signal and Information Processing, 2014

2001

Remote Ultrasound Diagnostic System.

Mamoru Mitsuishi, Shin'ichi Warisawa, Taishi Tsuda, Takuya Higuchi, Norihiro Koizumi, Hiroyuki Hashizume, Kazuo Fujiwara

Proceedings of the 2001 IEEE International Conference on Robotics and Automation, 2001