Follow
Shogo Seki
Shogo Seki
Verified email at hco.ntt.co.jp
Title
Cited by
Cited by
Year
Generalized multichannel variational autoencoder for underdetermined source separation
S Seki, H Kameoka, L Li, T Toda, K Takeda
2019 27th European Signal Processing Conference (EUSIPCO), 1-5, 2019
222019
Joint separation and dereverberation of reverberant mixtures with multichannel variational autoencoder
S Inoue, H Kameoka, L Li, S Seki, S Makino
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
192019
Underdetermined source separation based on generalized multichannel variational autoencoder
S Seki, H Kameoka, L Li, T Toda, K Takeda
IEEE Access 7, 168104-168115, 2019
162019
Voicegrad: Non-parallel any-to-many voice conversion with annealed langevin dynamics
H Kameoka, T Kaneko, K Tanaka, N Hojo, S Seki
arXiv preprint arXiv:2010.02977, 2020
72020
Robust Example Search Using Bottleneck Features for Example-Based Speech Enhancement.
A Ogawa, S Seki, K Kinoshita, M Delcroix, T Yoshioka, T Nakatani, ...
INTERSPEECH, 3733-3737, 2016
32016
ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
T Kaneko, K Tanaka, H Kameoka, S Seki
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
22022
Self-produced speech enhancement and suppression method using air-and body-conductive microphones
M Takada, S Seki, T Toda
2018 Asia-Pacific Signal and Information Processing Association Annual …, 2018
22018
Semi-Supervised Self-Produced Speech Enhancement and Suppression Based on Joint Source Modeling of Air- and Body-Conducted Signals Using Variational Autoencoder.
S Seki, M Takada, T Toda
INTERSPEECH, 4039-4043, 2020
12020
Stereophonic music separation based on non-negative tensor factorization with cepstrum regularization
S Seki, T Toda, K Takeda
2017 25th European Signal Processing Conference (EUSIPCO), 981-985, 2017
12017
Attentionpit: Soft Permutation Invariant Training for Audio Source Separation with Attention Mechanism
H Kameoka, S Seki, L Li, C Watanabe
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
2022
Investigation And Comparison of Optimization Methods for Variational Autoencoder-Based Underdetermined Multichannel Source Separation
S Seki, H Kameoka, L Li
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
2022
HBP: An Efficient Block Permutation Solver Using Hungarian Algorithm and Spectrogram Inpainting for Multichannel Audio Source Separation
L Li, H Kameoka, S Seki
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
2022
Singing Fundamental Frequency Contour Generation Using Generalized Command-Response Model and Score-Conditional Variational Autoencoder
S Seki, H Taga, T Toda
2021 IEEE 31st International Workshop on Machine Learning for Signal …, 2021
2021
Single-Channel Multispeaker Separation with Variational Autoencoder Spectrogram Model
N Murashima, H Kameoka, L Li, S Seki, S Makino
Journal of Signal Processing 25 (4), 145-149, 2021
2021
Semi-Supervised Enhancement and Suppression of Self-Produced Speech Using Correspondence between Air-and Body-Conducted Signals
M Takada, S Seki, PL Tobing, T Toda
2020 28th European Signal Processing Conference (EUSIPCO), 456-460, 2021
2021
Intelligibility Enhancement Based on Speech Waveform Modification Using Hearing Impairment.
S Hikosaka, S Seki, T Hayashi, K Kobayashi, K Takeda, H Banno, T Toda
INTERSPEECH, 4059-4063, 2020
2020
Self-produced speech enhancement and suppression method with wearable air-and body-conductive microphones
M Takada, S Seki, T Toda
IEICE Technical Report; IEICE Tech. Rep. 118 (190), 7-12, 2018
2018
Stereophonic Music Separation Based on Non-Negative Tensor Factorization with Cepstral Distance Regularization
S Seki, T Toda, K Takeda
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and …, 2018
2018
An investigation of singing voice separation methods for a statistical approach to singing voice modification in music
T Yamada, S Seki, K Kobayashi, T Toda
IEICE Technical Report; IEICE Tech. Rep. 117 (517), 209-214, 2018
2018
Missing component restoration for masked speech signals based on time-domain spectrogram factorization
S Seki, H Kameoka, T Toda, K Takeda
2017 IEEE 27th International Workshop on Machine Learning for Signal …, 2017
2017
The system can't perform the operation now. Try again later.
Articles 1–20