Shogo Seki

According to our database, Shogo Seki authored at least 31 papers between 2016 and 2024.

Collaborative distances:

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

2024

VoiceGrad: Non-Parallel Any-to-Many Voice Conversion With Annealed Langevin Dynamics.

Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Shogo Seki

IEEE ACM Trans. Audio Speech Lang. Process., 2024

Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio.

Li Li, Shogo Seki

CoRR, 2024

Remixed2remixed: Domain Adaptation for Speech Enhancement by Noise2noise Learning with Remixing.

Li Li, Shogo Seki

Proceedings of the IEEE International Conference on Acoustics, 2024

Audio Spotforming Using Nonnegative Tensor Factorization with Attractor-Based Regularization.

Shoma Ayano, Li Li, Shogo Seki, Daichi Kitamura

Proceedings of the 32nd European Signal Processing Conference, 2024

2023

Non-Parallel Whisper-to-Normal Speaking Style Conversion Using Auxiliary Classifier Variational Autoencoder.

Shogo Seki, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka

IEEE Access, 2023

CFVC: Conditional Filtering for Controllable Voice Conversion.

Kou Tanaka, Takuhiro Kaneko, Hirokazu Kameoka, Shogo Seki

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN.

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

JSV-VC: Jointly Trained Speaker Verification and Voice Conversion Models.

Shogo Seki, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko

Proceedings of the IEEE International Conference on Acoustics, 2023

Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis.

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki

Proceedings of the IEEE International Conference on Acoustics, 2023

W2N-AVSC: Audiovisual Extension For Whisper-To-Normal Speech Conversion.

Shogo Seki, Kanami Imamura, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Noboru Harada

Proceedings of the 31st European Signal Processing Conference, 2023

2022

Distilling Sequence-to-Sequence Voice Conversion Models for Streaming Conversion Applications.

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

MISRNet: Lightweight Neural Vocoder Using Multi-Input Single Shared Residual Blocks.

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki

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

CAUSE: Crossmodal Action Unit Sequence Estimation from Speech.

Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki, Kou Tanaka

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

Investigation And Comparison of Optimization Methods for Variational Autoencoder-Based Underdetermined Multichannel Source Separation.

Shogo Seki, Hirokazu Kameoka, Li Li

Proceedings of the IEEE International Conference on Acoustics, 2022

HBP: An Efficient Block Permutation Solver Using Hungarian Algorithm and Spectrogram Inpainting for Multichannel Audio Source Separation.

Li Li, Hirokazu Kameoka, Shogo Seki

Proceedings of the IEEE International Conference on Acoustics, 2022

ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform.

Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka, Shogo Seki

Proceedings of the IEEE International Conference on Acoustics, 2022

Attentionpit: Soft Permutation Invariant Training for Audio Source Separation with Attention Mechanism.

Hirokazu Kameoka, Shogo Seki, Li Li, Chihiro Watanabe

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Singing Fundamental Frequency Contour Generation Using Generalized Command-Response Model and Score-Conditional Variational Autoencoder.

Shogo Seki, Haruka Taga, Tomoki Toda

Proceedings of the 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), 2021

2020

A Study on Utilization of Prior Knowledge in Underdetermined Source Separation and Its Application.

Shogo Seki

PhD thesis, 2020

Semi-Supervised Self-Produced Speech Enhancement and Suppression Based on Joint Source Modeling of Air- and Body-Conducted Signals Using Variational Autoencoder.

Shogo Seki, Moe Takada, Tomoki Toda

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

Intelligibility Enhancement Based on Speech Waveform Modification Using Hearing Impairment.

Shu Hikosaka, Shogo Seki, Tomoki Hayashi, Kazuhiro Kobayashi, Kazuya Takeda, Hideki Banno, Tomoki Toda

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

Semi-Supervised Enhancement and Suppression of Self-Produced Speech Using Correspondence between Air- and Body-Conducted Signals.

Moe Takada, Shogo Seki, Patrick Lumban Tobing, Tomoki Toda

Proceedings of the 28th European Signal Processing Conference, 2020

2019

Underdetermined Source Separation Based on Generalized Multichannel Variational Autoencoder.

Shogo Seki, Hirokazu Kameoka, Li Li, Tomoki Toda, Kazuya Takeda

IEEE Access, 2019

Joint Separation and Dereverberation of Reverberant Mixtures with Multichannel Variational Autoencoder.

Shota Inoue, Hirokazu Kameoka, Li Li, Shogo Seki, Shoji Makino

Proceedings of the IEEE International Conference on Acoustics, 2019

Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation.

Shogo Seki, Hirokazu Kameoka, Li Li, Tomoki Toda, Kazuya Takeda

Proceedings of the 27th European Signal Processing Conference, 2019

2018

Stereophonic Music Separation Based on Non-Negative Tensor Factorization with Cepstral Distance Regularization.

Shogo Seki, Tomoki Toda, Kazuya Takeda

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2018

Self-Produced Speech Enhancement and Suppression Method using Air- and Body-Conductive Microphones.

Moe Takada, Shogo Seki, Tomoki Toda

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

2017

Sketch-based 3D hair posing by contour drawings.

Shogo Seki, Takeo Igarashi

Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation, 2017

Missing component restoration for masked speech signals based on time-domain spectrogram factorization.

Shogo Seki, Hirokazu Kameoka, Tomoki Toda, Kazuya Takeda

Proceedings of the 27th IEEE International Workshop on Machine Learning for Signal Processing, 2017

Stereophonic music separation based on non-negative tensor factorization with cepstrum regularization.

Shogo Seki, Tomoki Toda, Kazuya Takeda

Proceedings of the 25th European Signal Processing Conference, 2017

2016

Robust Example Search Using Bottleneck Features for Example-Based Speech Enhancement.

Atsunori Ogawa, Shogo Seki, Keisuke Kinoshita, Marc Delcroix, Takuya Yoshioka, Tomohiro Nakatani, Kazuya Takeda

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