Papers - TODA Tomoki
-
Weakly-supervised sound event detection with self-attention Reviewed International coauthorship
K. Miyazaki, T. Komatsu, T. Hayashi, S. Watanabe, T. Toda, K. Takeda
Proc. IEEE ICASSP page： 66 - 70 2020.5
-
ESPNET-TTS: Uunified, reproducible, and integratable open source end-to-end text-to-speech toolkit Reviewed International coauthorship
T. Hayashi, R. Yamamoto, K. Inoue, T. Yoshimura, S. Watanabe, T. Toda, K. Takeda, Y. Zhang, X. Tan
Proc. IEEE ICASSP page： 7654 - 7658 2020.5
-
Efficient shallow WaveNet vocoder using multiple samples output based on Laplacian distribution and linear prediction Reviewed
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. IEEE ICASSP page： 7204 - 7208 2020.5
-
Transformer-based text-to-speech with weighted forced attention Reviewed
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP page： 6729 - 6733 2020.5
-
Non-parallel voice conversion system with WaveNet vocoder and collapsed speech suppression Reviewed
Y.-C. Wu, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda
IEEE Access Vol. 8 ( 1 ) page： 62094 - 62106 2020.4
-
LMS経由で手書きレポートを返却するWebサービス「かみレポ」の開発・評価 Reviewed
大平 茂輝, 清谷 峻也, 伊藤 瑠哉, 岡本 康佑, 谷川 右京, 出口 大輔, 戸田 智基
情報処理学会論文誌：教育とコンピュータ Vol. 6 ( 1 ) page： 52 - 68 2020.2
-
Customer satisfaction estimation in contact center calls based on a hierarchical multi-task model Reviewed
A. Ando, R. Masumura, H. Kamiyama, S. Kobashikawa, Y. Aono, T. Toda
IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28 ( 1 ) page： 715 - 728 2020.1
-
Investigation of shallow WaveNet vocoder with Laplacian distribution output Reviewed
P.L. Tobing, T. Hayashi, T. Toda
Proc. IEEE ASRU page： 176 - 183 2019.12
-
Tacotron-based acoustic model using phoneme alignment for practical neural text-to-speech synthesis Reviewed
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ASRU page： 214 - 221 2019.12
-
Underdetermined source separation based on generalized multichannel variational autoencoder Reviewed
S. Seki, H. Kameoka, L. Li, T. Toda, K. Takeda
IEEE Access Vol. 7 ( 1 ) page： 168104 - 168115 2019.12
-
Voice conversion with CycleRNN-based spectral mapping and finely-tuned WaveNet vocoder Reviewed
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
IEEE Access Vol. 7 ( 1 ) page： 171114 - 171125 2019.12
-
機械学習と音声生成：音声波形モデリングの進展
戸田 智基
計測と制御 Vol. 58 ( 12 ) page： 951 - 954 2019.12
-
Improving singing aid system for laryngectomees with statistical voice conversion and VAE-SPACE Reviewed
L. Li, T. Toda, K. Morikawa, K. Kobayashi, S. Makino
Proc. ISMIR page： 784 - 790 2019.11
-
Development of a real-time bionic voice generation system based on statistical excitation prediction Reviewed International coauthorship
F. Ahmadi, K. Kobayashi, T. Toda
Proc. ACM ASSETS page： 655 - 657 2019.10
-
Robustness of statistical voice conversion based on direct waveform modification against background sounds Reviewed
Y. Kurita, K. Kobayashi, K. Takeda, T. Toda
Proc. INTERSPEECH page： 684 - 688 2019.9
-
Non-parallel voice conversion with cyclic variational autoencoder Reviewed
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. INTERSPEECH page： 674 - 678 2019.9
-
Quasi-periodic WaveNet vocoder: a pitch dependent dilated convolution model for parametric speech generation Reviewed
Y.-C. Wu, T. Hayashi, P.L. Tobing, K. Kobayashi, T. Toda
Proc. INTERSPEECH page： 196 - 200 2019.9
-
Refined WaveNet vocoder for variational autoencoder based voice conversion Reviewed International coauthorship
W.-C. Huang, Y.-C. Wu, H.-T. Hwang, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda, Y. Tsao, H.-M. Wang
Proc. EUSIPCO page： 5 pages 2019.9
-
Generalized multichannel variational autoencoder for underdetermined source separation Reviewed
S. Seki, H. Kameoka, L. Li, T. Toda, K. Takeda
Proc. EUSIPCO page： 5 pages 2019.9
-
Investigation of F0 conditioning and fully convolutional networks in variational autoencoder based voice conversion Reviewed International coauthorship
W.-C. Huang, Y.-C. Wu, C.-C. Lo, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda, Y. Tsao, H.-M. Wang
Proc. INTERSPEECH page： 709 - 713 2019.9