論文 - 戸田 智基
-
Audio difference learning for audio captioning 査読有り
T. Komatsu, Y. Fujita, K. Takeda, T. Toda
Proc. IEEE ICASSP 頁: 1456 - 1460 2024年4月
-
ConvNeXt-TTS and ConvNeXt-VC: ConvNeXt-based fast end-to-end sequence-to-sequence text-to-speech and voice conversion 査読有り
T. Okamoto, Y. Ohtani, T. Toda, H. Kawai
Proc. IEEE ICASSP 頁: 12456 - 12460 2024年4月
-
MF-AED-AEC: speech emotion recognition by leveraging multimodal fusion, ASR error detection, and ASR error correction 査読有り 国際共著
J. He, X. Shi, X. Li, T. Toda
Proc. IEEE ICASSP 頁: 11066 - 11070 2024年4月
-
Electrolaryngeal speech intelligibility enhancement through robust linguistic encoders 査読有り
L.P. Violeta, W.-C. Huang, D. Ma, R. Yamamoto, K. Kobayashi, T. Toda
Proc. IEEE ICASSP 頁: 10961 - 10965 2024年4月
-
FIRNET: fundamental frequency controllable fast neural vocoder with trainable finite impulse response filter 査読有り
Y. Ohtani, T. Okamoto, T. Toda, H. Kawai
Proc. IEEE ICASSP 頁: 10871 - 10875 2024年4月
-
Dual-channel target speaker extraction based on conditional variational autoencoder and directional information 査読有り
R. Wang, L. Li, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 32 巻 頁: 12 pages 2024年3月
-
Fast neural speech waveform generative models with fully-connected layer-based upsampling 査読有り
H. Yamashita, T. Okamoto, R. Takashima, Y. Ohtani, T. Takiguchi, T. Toda, H. Kawai
IEEE Access 12 巻 頁: 31409 - 31421 2024年2月
-
喉頭摘出者における音声収録アプリを用いた術前音声の保存 ―Save the Voice プロジェクト― 査読有り
西尾 直樹, 戸田 智基, 小林 和弘, 三谷 壮平, 飴矢 美里, 向山 宣昭, 木村 宏之, 徳倉 達也, 坪井 崇, 藤本 保志, 曾根 三千彦
喉頭 35 巻 ( 2 ) 頁: 142 - 147 2023年12月
-
The Singing Voice Conversion Challenge 2023 査読有り 国際共著
W.-C. Huang, L.P. Violeta, S. Liu, J. Shi, T. Toda
Proc. IEEE ASRU 頁: 8 pages 2023年12月
-
ED-CEC: improving rare word recognition using ASR post-processing based on error detection and context-aware error correction 査読有り
J. He, Z. Yang, T. Toda
Proc. IEEE ASRU 頁: 6 pages 2023年12月
-
Improving severity preservation of healthy-to-pathological voice conversion with global style tokens 査読有り 国際共著
B. Halpern, W.-C. Huang, L.P. Violeta, R. van Son, T. Toda
Proc. IEEE ASRU 頁: 7 pages 2023年12月
-
A comparative study of voice conversion models with large-scale speech and singing data: the T13 systems for the Singing Voice Conversion Challenge 2023 査読有り
R. Yamamoto, R. Yoneyama, L.P. Violeta, W.-C. Huang, T. Toda
Proc. IEEE ASRU 頁: 6 pages 2023年12月
-
The VoiceMOS Challenge 2023: zero-shot subjective speech quality prediction for multiple domains 査読有り 国際共著
E. Cooper, W.-C. Huang, Y. Tsao, H.-M. Wang, T. Toda, J. Yamagishi
Proc. IEEE ASRU 頁: 7 pages 2023年12月
-
WaveNeXt: ConvNeXt-based fast neural vocoder without iSTFT layer 査読有り
T. Okamoto, H. Yamashita, Y. Ohtani, T. Toda, H. Kawai
Proc. IEEE ASRU 頁: 8 pages 2023年12月
-
Sequence-to-sequence network training methods for automatic guitar transcription with tokenized outputs 査読有り
S. Kim, K. Takeda, T. Toda
Proc. ISMIR 頁: 524 - 531 2023年11月
-
Evaluating methods for ground-truth-free foreign accent conversion 査読有り
W.-C. Huang, T. Toda
Proc. APSIPA ASC 頁: 1136 - 1141 2023年11月
-
An analysis of personalized speech recognition system development for the deaf and hard-of-hearing 査読有り
L.P. Violeta, T. Toda
Proc. APSIPA ASC 頁: 1851 - 1856 2023年11月
-
Semi-supervised multimodal emotion recognition with consensus decision-making and label correction 査読有り 国際共著
J. Tian, D. Hu, X. Shi, J. He, X. Li, Y. Gao, T. Toda, X. Xu, X. Hu
Proc. MRAC 頁: 67 - 73 2023年10月
-
Differentiable representation of warping based on Lie group theory 査読有り
A. Miyashita, T. Toda
Proc. IEEE WASPAA 頁: 5 pages 2023年10月
-
Directional target speaker extraction under noisy underdetermined conditions through conditional variational autoencoder with global style tokens 査読有り
R. Wang, T. Toda
Proc. IEEE WASPAA 頁: 5 pages 2023年10月
-
Sound field interpolation with unsupervised calibration for freely spaced circular microphone array in rotation-robust beamforming 査読有り
S. Luan, Y. Wakabayashi, T. Toda
Proc.EUSIPCO 頁: 21 - 25 2023年9月
-
Noisy-to-noisy voice conversion under variations of noisy condition 査読有り
C. Xie, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 31 巻 頁: 3871 - 3882 2023年9月
-
High-fidelity and pitch-controllable neural vocoder based on unified source-filter networks 査読有り
R. Yoneyama, Y.-C. Wu, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 31 巻 頁: 3717 - 3729 2023年9月
-
Preference-based training framework for automatic speech quality assessment using deep neural network 査読有り
C.-H. Hu, Y. Yasuda, T. Toda
Proc. INTERSPEECH 頁: 546 - 550 2023年8月
-
Analysis of mean opinion scores in subjective evaluation of synthetic speech based on tail probabilities 査読有り
Y. Yasuda, T. Toda
Proc. INTERSPEECH 頁: 5491 - 5495 2023年8月
-
Reverberation-controllable voice conversion using reverberation time estimator 査読有り
Y. Choi, C. Xie, T. Toda
Proc. INTERSPEECH 頁: 2103 - 2107 2023年8月
-
E2E-S2S-VC: end-to-end sequence-to-sequence voice conversion 査読有り
T. Okamoto, H. Yamashita, T. Toda, H. Kawai
Proc. INTERSPEECH 頁: 2043 - 2047 2023年8月
-
Emotion awareness in multi-utterance turn for improving emotion prediction in multi-speaker conversation 査読有り 国際共著
X. Shi, X. Li, T. Toda
Proc. INTERSPEECH 頁: 765 - 769 2023年8月
-
Representation of vocal tract length transformation based on group theory 査読有り
A. Miyashita, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
Analysis of Noisy-target Training for DNN-based speech enhancement 査読有り
T. Fujimura, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
Intermediate fine-tuning using imperfect synthetic speech for improving electrolaryngeal speech recognition 査読有り
L.P. Violeta, D. Ma, W.-C. Huang, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
Source-Filter HiFiGAN: fast and pitch controllable high-fidelity neural vocoder 査読有り 国際共著
R. Yoneyama, Y.-C. Wu, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
NNSVS: a neural network based singing voice synthesis toolkit 査読有り
R. Yamamoto, R. Yoneyama, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
Low-latency electrolaryngeal speech enhancement based on FastSpeech2-based voice conversion and self-supervised speech representation 査読有り
K. Kobayashi, T. Hayashi, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoder 査読有り
Y. Yasuda, T. Toda
Proc. IEEE ICASSP 頁: 5 pages 2023年6月
-
Harmonic-Net: fundamental frequency and speech rate controllable fast neural vocoder 査読有り
K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, H. Kawai
IEEE/ACM Transactions on Audio, Speech and Language Processing 31 巻 頁: 1902 - 1915 2023年5月
-
Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion 査読有り
D. Ma, L.P. Violeta, K. Kobayashi, T. Toda
Proc. IEEE SLT 頁: 949 - 954 2023年1月
-
Music similarity calculation of individual instrumental sounds using metric learning 査読有り
Y. Hashizume, L. Li, T. Toda
Proc. APSIPA ASC 頁: 33 - 38 2022年11月
-
Sequence-wise optimization for quasi-harmonic speech waveform modeling 査読有り
S. Chen, T. Toda
Proc. APSIPA ASC 頁: 1658 - 1663 2022年11月
-
Direction-aware target speaker extraction with a dual-channel system based on conditional variational autoencoders under underdetermined conditions 査読有り
R. Wang, L. Li, T. Toda
Proc. APSIPA ASC 頁: 347 - 353 2022年11月
-
Interpretable control for emotional text-to-speech system toward development of sympathetic educational-support robots 査読有り
J. Feng, T. Yoshikawa, T. Toda
Proc. APSIPA ASC 頁: 342 - 346 2022年11月
-
Investigation of Japanese Png BERT language model in text-to-speech synthesis for pitch accent language 査読有り
Y. Yasuda, T. Toda
IEEE Journal of Selected Topics in Signal Processing 16 巻 ( 6 ) 頁: 1319 - 1328 2022年10月
-
A comparative study of self-supervised speech representation based voice conversion 査読有り 国際共著
W.-C. Huang, S.-W. Yang, T. Hayashi, T. Toda
IEEE Journal of Selected Topics in Signal Processing 16 巻 ( 6 ) 頁: 1308 - 1318 2022年10月
-
Noisy-to-noisy voice conversion with pre-training strategy 招待有り 査読有り
C. Xie, T. Toda
Proc. ICA 頁: 5 pages 2022年9月
-
A cyclical approach to synthetic and natural speech mismatch refinement of neural post-filter for low-cost text-to-speech system 査読有り
Y.-C. Wu, P.L. Tobing, K. Yasuhara, N. Matsunaga, Y. Ohtani, T. Toda
APSIPA Transactions on Signal and Information Processing 11 巻 ( e30 ) 頁: 1 - 32 2022年9月
-
Investigating self-supervised pretraining frameworks for pathological speech recognition 査読有り
L.P. Violeta, W.-C. Huang, T. Toda
Proc. INTERSPEECH 頁: 41 - 45 2022年9月
-
Unified source-filter GAN with harmonic-plus-noise source excitation generation 査読有り
R. Yoneyama, Y.-C. Wu, T. Toda
Proc. INTERSPEECH 頁: 848 - 852 2022年9月
-
The VoiceMOS Challenge 2022 査読有り 国際共著
W.-C. Huang, E. Cooper, Y. Tsao, H.-M. Wang, T. Toda, J. Yamagishi
Proc. INTERSPEECH 頁: 4536 - 4540 2022年9月
-
Spoken-text-style transfer with conditional variational autoencoder and content word storage 査読有り
D. Yoshioka, Y. Yaduda, N. Matsunaga, Y. Ohtani, T. Toda
Proc. INTERSPEECH 頁: 4576 - 4580 2022年9月
-
An evaluation of three-stage voice conversion framework for noisy and reverberant conditions 査読有り
Y. Choi, C. Xie, T. Toda
Proc. INTERSPEECH 頁: 4910 - 4914 2022年9月
-
Improvement of anomalous sound detection method considering the distribution of embedding 招待有り 査読有り
I. Kuroyanagi, T. Hayashi, K. Takeda, T. Toda
Proc. ICA 頁: 5 pages 2022年9月
-
Modified sound field interpolation method for rotation-robust beamforming with unequally spaced circular microphone array 査読有り
S. Luan, Y. Wakabayashi, T. Toda
Proc. EUSIPCO 頁: 344 - 348 2022年8月
-
Note-level automatic guitar transcription using attention mechanism 査読有り
S. Kim, T. Hayashi, T. Toda
Proc. EUSIPCO 頁: 229 - 233 2022年8月
-
Improvement of serial approach to anomalous sound detection by incorporating two binary cross-entropies for outlier exposure 査読有り
I. Kuroyanagi, T. Hayashi, K. Takeda, T. Toda
Proc. EUSIPCO 頁: 294 - 298 2022年8月
-
Generalization ability of MOS prediction networks 査読有り
E. Cooper, W.-C. Huang, T. Toda, J. Yamagishi
Proc. IEEE ICASSP 頁: 8442 - 8446 2022年5月
-
LDNet: unified listener dependent modeling in MOS prediction for synthetic speech 査読有り
W.-C. Huang, E. Cooper, J. Yamagishi, T. Toda
Proc. IEEE ICASSP 頁: 896 - 900 2022年5月
-
S3PRL-VC: open-source voice conversion framework with self-supervised speech representations 査読有り 国際共著
W.-C. Huang, S.-W. Yang, T. Hayashi, H.-Y. Lee, S. Watanabe, T. Toda
Proc. IEEE ICASSP 頁: 6552 - 6556 2022年5月
-
Towards identity preserving normal to dysarthric voice conversion 査読有り 国際共著
W.-C. Huang, B.M Halpern, L.P. Violeta, O. Scharenborg, T. Toda
Proc. IEEE ICASSP 頁: 6672 - 6676 2022年5月
-
Direct noisy speech modeling for noisy-to-noisy voice conversion 査読有り
C. Xie, Y-.C. Wu, P.L. Tobing, W-.C. Huang, T. Toda
Proc. IEEE ICASSP 頁: 6787 - 6791 2022年5月
-
An investigation of streaming non-autoregressive sequence-to-sequence voice conversion 査読有り
T. Hayashi, K. Kobayashi, T. Toda
Proc. IEEE ICASSP 頁: 6802 - 6806 2022年5月
-
Comparison of real-time multi-speaker neural vocoders on CPUs 査読有り
K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, H. Kawai
Acoustical Science and Technology, Acoustical Letter 43 巻 ( 2 ) 頁: 121 - 124 2022年3月
-
Neural speech-rate conversion with multispeaker WaveNet vocoder 査読有り
T. Okamoto, K. Matsubara, T. Toda, Y. Shiga, H. Kawai
Speech Communication 138 巻 頁: 1 - 12 2022年3月
-
S3PRL-VC: open-source voice conversion framework with self-supervised speech representations 査読有り 国際共著
W.-C. Huang, S.-W. Yang, T. Hayashi, H.-Y. Lee, S. Watanabe, T. Toda
Proc. AAAI-22 Workshop, W35: Self-Supervised Learning for Audio and Speech Processing 頁: 5 pages 2022年2月
-
Time alignment using lip images for frame-based electrolaryngeal voice conversion 査読有り 国際共著
Y.-S. Liou, W.-C. Huang, M.-C. Yen, S.-W. Tsai, Y.-H. Peng, T. Toda, Y. Tsao, H.-M. Wang
Proc. APSIPA ASC 頁: 1234 - 1238 2021年12月
-
Multi-stream HiFi-GAN with data-driven waveform decomposition 査読有り
T. Okamoto, T. Toda, H. Kawai
Proc. IEEE ASRU 頁: 610 - 617 2021年12月
-
On prosody modeling for ASR+TTS based voice conversion 査読有り 国際共著
W.-C. Huang, T. Hayashi, X. Li, S. Watanabe, T. Toda
Proc. IEEE ASRU 頁: 642 - 649 2021年12月
-
Mandarin electrolaryngeal speech voice conversion with sequence-to-sequence modeling 査読有り 国際共著
M.-C. Yen, W.-C. Huang, K. Kobayashi, Y.-H. Peng, S.-W. Tasi, Y. Tsao, T. Toda, J.-S. R. Jang, H.-M. Wang
Proc. IEEE ASRU 頁: 650 - 657 2021年12月
-
HASA-Net: a non-intrusive hearing-aid speech assessment network 査読有り 国際共著
H.-T. Chiang, Y.-C. Wu, C. Yu, T. Toda, H.-M. Wang, Y.-C. Hu, Y. Tsao
Proc. IEEE ASRU 頁: 907 - 913 2021年12月
-
Mandarin electro-laryngeal speech enhancement based on statistical voice conversion and manual tone control 査読有り 国際共著
Z. Qian, H. Niu, L. Wang, K. Kobayashi, S. Zhang, T. Toda
Proc. APSIPA ASC 頁: 546 - 552 2021年12月
-
Noisy-to-noisy voice conversion framework with denoising model 査読有り
C. Xie, Y.-C. Wu, P.L. Tobing, W.-C. Huang, T. Toda
Proc. APSIPA ASC 頁: 814 - 820 2021年12月
-
Investigation of text-to-speech-based synthetic parallel data for sequence-to-sequence non-parallel voice conversion 査読有り
D. Ma, W.-C. Huang, T. Toda
Proc. APSIPA ASC 頁: 870 - 877 2021年12月
-
An ensemble approach to anomalous sound detection based on conformer-based autoencoder and binary classifier incorporated with metric learning 査読有り
I. Kuroyanagi, T. Hayashi, Y. Adachi, T. Yoshimura, K. Takeda, T. Toda
Proc. DCASE 2021 Workshop 頁: 110 - 114 2021年11月
-
Singing fundamental frequency contour generation using generalized command response model and score-conditional variational autoencoder 査読有り
S. Seki, H. Taga, T. Toda
Proc. IEEE MLSP 頁: 1 - 6 2021年10月
-
Singing fundamental frequency contour generation using generalized command response model and score-conditional variational autoencoder 査読有り
S. Seki, H. Taga, T. Toda
Proc. IEEE MLSP 頁: 6 pages 2021年10月
-
Anomalous sound detection using a binary classification model and class centroids 査読有り
I. Kuroyanagi, T. Hayashi, K. Takeda, T. Toda
Proc. EUSIPCO 頁: 1995 - 1999 2021年8月
-
学習支援サービスの運用とオンデマンド型を中心としたオンライン授業への展開――名古屋大学における事例―― 招待有り
戸田 智基, 大平 茂輝, 後藤 明史, 出口 大輔, 森 健策
電子情報通信学会誌 104 巻 ( 8 ) 頁: 862 - 866 2021年8月
-
Relational data selection for data augmentation of speaker-dependent multi-band MelGAN vocoder 査読有り 国際共著
Y.-C. Wu, C.-H. Hu, H.-S. Lee, Y.-H. Peng, W.-C. Huang, Y. Tsao, H.-M. Wang, T. Toda
Proc. INTERSPEECH 頁: 3630 - 3634 2021年8月
-
High-fidelity and low-latency universal neural vocoder based on multiband WaveRNN with data-driven linear prediction for discrete waveform modeling 査読有り
P.L. Tobing, T. Toda
Proc. INTERSPEECH 頁: 2217 - 2221 2021年8月
-
Unified source-filter GAN: unified source-filter network based on factorization of quasi-periodic parallel WaveGAN 査読有り
R. Yoneyama, Y.-C. Wu, T. Toda
Proc. INTERSPEECH 頁: 2187 - 2191 2021年8月
-
A preliminary study of a two-stage paradigm for preserving speaker identity in dysarthric voice conversion 査読有り 国際共著
W.-C. Huang, K. Kobayashi, Y.-H. Peng, C.-F. Liu, Y. Tsao, H.-M. Wang, T. Toda
Proc. INTERSPEECH 頁: 1329 - 1333 2021年8月
-
Low-latency real-time non-parallel voice conversion based on cyclic variational autoencoder and multiband WaveRNN with data-driven linear prediction 査読有り
P.L. Tobing, T. Toda
Proc. 11th ISCA Speech Synthesis Workshop (SSW11) 頁: 142 - 147 2021年8月
-
Full-band LPCNet: a real-time neural vocoder for 48 kHz audio with a CPU 査読有り
K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, Y. Shiga, H. Kawai
IEEE Access 9 巻 頁: 94923 - 94933 2021年7月
-
Crank: an open-source software for nonparallel voice conversion based on vector-quantized variational autoencoder 査読有り
K. Kobayashi, W.-C. Huang, Y.-C. Wu, P.L. Tobing, T. Hayashi, T. Toda
Proc. IEEE ICASSP 頁: 5934 - 5938 2021年6月
-
Any-to-one sequence-to-sequence voice conversion using self-supervised discrete speech representations 査読有り
W.-C. Huang, Y.-C. Wu, T. Hayashi, T. Toda
Proc. IEEE ICASSP 頁: 5944 - 5948 2021年6月
-
Speech recognition by simply fine-tuning BERT 査読有り 国際共著
W.-C. Huang, C.-H. Wu, S.-B. Luo, K.-Y. Chen, H.-M. Wang, T. Toda
Proc. IEEE ICASSP 頁: 7343 - 7347 2021年6月
-
Non-autoregressive sequence-to-sequence voice conversion 査読有り
T. Hayashi, W.-C. Huang, K. Kobayashi, T. Toda
Proc. IEEE ICASSP 頁: 7068 - 7072 2021年6月
-
High-intelligibility speech synthesis for dysarthric speakers with LPCNet-based TTS and CycleVAE-based VC 査読有り
K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP 頁: 7058 - 7062 2021年6月
-
Speech emotion recognition based on listener adaptive models 査読有り
A. Ando, R. Masumura, H. Sato, T. Moriya, T. Ashihara, Y. Ijima, T. Toda
Proc. IEEE ICASSP 頁: 6274 - 6278 2021年6月
-
Noise level limited sub-modeling for diffusion probabilistic vocoders 査読有り
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP 頁: 6029 - 6033 2021年6月
-
Speech emotion recognition based on listener-dependent emotion perception models 査読有り
A. Ando, T. Mori, S. Kobashikawa, T. Toda
APSIPA Transactions on Signal and Information Processing 10 巻 ( e6 ) 頁: 1 - 11 2021年4月
-
Quasi-periodic WaveNet: an autoregressive raw waveform generative model with pitch-dependent dilated convolution neural network 査読有り
Y.-C. Wu, T. Hayashi, P.L. Tobing, K. Kobayashi, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 29 巻 頁: 1134 - 1148 2021年3月
-
Pretraining techniques for sequence-to-sequence voice conversion 査読有り
W.-C. Huang, T. Hayashi, Y.-C. Wu, H. Kameoka, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 29 巻 頁: 745 - 755 2021年2月
-
Quasi-periodic parallel WaveGAN: a non-autoregressive raw waveform generative model with pitch-dependent dilated convolution neural network 査読有り
Y.-C. Wu, T. Hayashi, T. Okamoto, H. Kawai, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 29 巻 頁: 792 - 806 2021年2月
-
Investigation of training data size for real-time neural vocoders on CPUs 査読有り
K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, Y. Shiga, H. Kawai
Acoustical Science and Technology, Acoustical Letter 42 巻 ( 1 ) 頁: 65 - 68 2021年1月
-
Many-to-many voice transformer network 査読有り
H. Kameoka, W.-C. Huang, K. Tanaka, T. Kaneko, N. Hojo, T. Toda
IEEE/ACM Transactions on Audio, Speech and Language Processing 29 巻 頁: 656 - 670 2021年1月
-
Cross-lingual voice conversion using cyclic variational auto-encoder and a WaveNet vocoder 査読有り
H. Nakatani, P.L. Tobing, K. Takeda, T. Toda
Proc. APSIPA ASC 頁: 520 - 526 2020年12月
-
Phoneme embeddings on predicting fundamental frequency pattern for electrolaryngeal speech 査読有り
M. Eshghi, K. Kobayashi, K. Tanaka, H. Kameoka, T. Toda
Proc. APSIPA ASC 頁: 572 - 577 2020年12月
-
ASVspoof 2019: a large-scale public database of synthetic, converted and replayed speech 査読有り 国際共著
X. Wang, J. Yamagishi, M. Todisco, H. Delgado, A. Nautsch, N. Evans, M. Sahidullah, V. Vestman, T. Kinnunen, K.A. Lee, L. Juvela, P. Alku, Y.-H. Peng, H.-T. Hwang, Y. Tsao, H.-M. Wang, S. Le Maguer, M. Becker, F. Henderson, R. Clark, Y. Zhang, Q. Wang, Y. Jia, K. Onuma, K. Mushika, T. Kaneda, Y. Jiang, L.-J. Liu, Y.-C. Wu, W.-C. Huang, T. Toda, K. Tanaka, H. Kameoka, I. Steiner, D. Matrouf, J.-F. Bonastre, A. Govender, S. Ronanki, J.-X. Zhang, Z.-H. Ling
Computer Speech and Language 64 巻 ( Article 101114 ) 頁: 1 - 27 2020年11月
-
Conformer-based sound event detection with semi-supervised learning and data augmentation 査読有り 国際共著
K. Miyazaki, T. Komatsu, T. Hayashi, S. Watanabe, T. Toda, K. Takeda
Proc. DCASE 2020 Workshop 頁: 100 - 104 2020年11月
-
An evaluation of voice conversion with neural network spectral mapping models and WaveNet vocoder 査読有り
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
APSIPA Transactions on Signal and Information Processing 9 巻 ( e26, ) 頁: 1 - 14 2020年11月
-
Quasi-periodic parallel WaveGAN vocoder: a non-autoregressive pitch-dependent dilated convolution model for parametric speech generation 査読有り
Y.-C. Wu, T. Hayashi, T. Okamoto, H. Kawai, T. Toda
Proc. INTERSPEECH 頁: 3535 - 3539 2020年10月
-
The NU voice conversion system for the Voice Conversion Challenge 2020: on the effectiveness of sequence-to-sequence models and autoregressive neural vocoders 査読有り
W.-C. Huang, P.L. Tobing, Y.-C. Wu, K. Kobayashi, T. Toda
Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 頁: 165 - 169 2020年10月
-
The sequence-to-sequence baseline for the Voice Conversion Challenge 2020: cascading ASR and TTS 査読有り 国際共著
W.-C. Huang, T. Hayashi, S. Watanabe, T. Toda
Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 頁: 160 - 164 2020年10月
-
Baseline system of Voice Conversion Challenge 2020 with cyclic variational autoencoder and parallel WaveGAN 査読有り
P.L. Tobing, Y.-C. Wu, T. Toda
Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 頁: 155 - 159 2020年10月
-
Predictions of subjective ratings and spoofing assessments of Voice Conversion Challenge 2020 submissions 査読有り 国際共著
R.K. Das, T. Kinnunen, W.-C. Huang, Z. Ling, J. Yamagishi, Z. Yi, X. Tian, T. Toda
Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 頁: 99 - 120 2020年10月
-
Voice Conversion Challenge 2020 -- intra-lingual semi-parallel and cross-lingual voice conversion -- 査読有り 国際共著
Z. Yi, W.-C. Huang, X. Tian, J. Yamagishi, R.K. Das, T. Kinnunen, Z. Ling, T. Toda
Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 頁: 80 - 98 2020年10月
-
Cyclic spectral modeling for unsupervised unit discovery into voice conversion with excitation and waveform modeling 査読有り
P.L. Tobing, T. Hayashi, Y.-C. Wu, K. Kobayashi, T. Toda
Proc. INTERSPEECH 頁: 4861 - 4865 2020年10月
-
Voice transformer network: sequence-to-sequence voice conversion using transformer with text-to-speech pretraining 査読有り
W.-C. Huang, T. Hayashi, Y.-C. Wu, H. Kameoka, T. Toda
Proc. INTERSPEECH 頁: 4676 - 4680 2020年10月
-
Intelligibility enhancement based on speech waveform modification using hearing impairment simulator 査読有り
S. Hikosaka, S. Seki, T. Hayashi, K. Kobayashi, K. Takeda, H. Banno, T. Toda
Proc. INTERSPEECH 頁: 4059 - 4063 2020年10月
-
Semi-supervised self-produced speech enhancement and suppression based on joint source modeling of air- and body-conducted signals using variational autoencoder 査読有り
S. Seki, M. Takada, T. Toda
Proc. INTERSPEECH 頁: 4039 - 4043 2020年10月
-
A cyclical post-filtering approach to mismatch refinement of neural vocoder for text-to-speech systems 査読有り
Y.-C. Wu, P.L. Tobing, K. Yasuhara, N. Matsunaga, Y. Ohtani, T. Toda
Proc. INTERSPEECH 頁: 3540 - 3544 2020年10月
-
Implementation of low-latency electrolaryngeal speech enhancement based on multi-task CLDNN 査読有り
K. Kobayashi, T. Toda
Proc. EUSIPCO 頁: 396 - 400 2020年8月
-
Semi-supervised enhancement and suppression of self-produced speech using correspondence between air- and body-conducted signals 査読有り
M. Takada, S. Seki, P.L. Tobing, T. Toda
Proc. EUSIPCO 頁: 456 - 460 2020年8月
-
Weakly-supervised sound event detection with self-attention 査読有り 国際共著
K. Miyazaki, T. Komatsu, T. Hayashi, S. Watanabe, T. Toda, K. Takeda
Proc. IEEE ICASSP 頁: 66 - 70 2020年5月
-
ESPNET-TTS: Uunified, reproducible, and integratable open source end-to-end text-to-speech toolkit 査読有り 国際共著
T. Hayashi, R. Yamamoto, K. Inoue, T. Yoshimura, S. Watanabe, T. Toda, K. Takeda, Y. Zhang, X. Tan
Proc. IEEE ICASSP 頁: 7654 - 7658 2020年5月
-
Efficient shallow WaveNet vocoder using multiple samples output based on Laplacian distribution and linear prediction 査読有り
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. IEEE ICASSP 頁: 7204 - 7208 2020年5月
-
Transformer-based text-to-speech with weighted forced attention 査読有り
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP 頁: 6729 - 6733 2020年5月
-
Non-parallel voice conversion system with WaveNet vocoder and collapsed speech suppression 査読有り
Y.-C. Wu, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda
IEEE Access 8 巻 ( 1 ) 頁: 62094 - 62106 2020年4月
-
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 査読有り
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 6 巻 ( 1 ) 頁: 52 - 68 2020年2月
-
Customer satisfaction estimation in contact center calls based on a hierarchical multi-task model 査読有り
A. Ando, R. Masumura, H. Kamiyama, S. Kobashikawa, Y. Aono, T. Toda
IEEE/ACM Transactions on Audio, Speech, and Language Processing 28 巻 ( 1 ) 頁: 715 - 728 2020年1月
-
Investigation of shallow WaveNet vocoder with Laplacian distribution output 査読有り
P.L. Tobing, T. Hayashi, T. Toda
Proc. IEEE ASRU 頁: 176 - 183 2019年12月
-
Tacotron-based acoustic model using phoneme alignment for practical neural text-to-speech synthesis 査読有り
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ASRU 頁: 214 - 221 2019年12月
-
Underdetermined source separation based on generalized multichannel variational autoencoder 査読有り
S. Seki, H. Kameoka, L. Li, T. Toda, K. Takeda
IEEE Access 7 巻 ( 1 ) 頁: 168104 - 168115 2019年12月
-
Voice conversion with CycleRNN-based spectral mapping and finely-tuned WaveNet vocoder 査読有り
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
IEEE Access 7 巻 ( 1 ) 頁: 171114 - 171125 2019年12月
-
機械学習と音声生成:音声波形モデリングの進展 招待有り
戸田 智基
計測と制御 58 巻 ( 12 ) 頁: 951 - 954 2019年12月
-
Improving singing aid system for laryngectomees with statistical voice conversion and VAE-SPACE 査読有り
L. Li, T. Toda, K. Morikawa, K. Kobayashi, S. Makino
Proc. ISMIR 頁: 784 - 790 2019年11月
-
Development of a real-time bionic voice generation system based on statistical excitation prediction 査読有り 国際共著
F. Ahmadi, K. Kobayashi, T. Toda
Proc. ACM ASSETS 頁: 655 - 657 2019年10月
-
統計的手法による音響イベント検出 招待有り
林 知樹, 戸田 智基
日本音響学会誌 75 巻 ( 9 ) 頁: 532 - 537 2019年9月
-
An investigation of features for fundamental frequency pattern prediction in electrolaryngeal speech enhancement 査読有り
M. Eshghi, K. Tanaka, K. Kobayashi, H. Kameoka, T. Toda
Proc. 10th ISCA Speech Synthesis Workshop (SSW10) 頁: 251 - 256 2019年9月
-
Statistical voice conversion with quasi-periodic WaveNet vocoder 査読有り
Y.-C. Wu, T. Hayashi, P.L. Tobing, K. Kobayashi, T. Toda
Proc. 10th ISCA Speech Synthesis Workshop (SSW10) 頁: 63 - 68 2019年9月
-
Generalization of spectrum differential based direct waveform modification for voice conversion 査読有り 国際共著
W.-C. Huang, Y.-C. Wu, K. Kobayashi, Y.-H. Peng, H.-T. Hwang, P.L. Tobing, Y. Tsao, H.-M. Wang, T. Toda
Proc. 10th ISCA Speech Synthesis Workshop (SSW10) 頁: 57 - 62 2019年9月
-
Pre-trained text embeddings for enhanced text-to-speech synthesis 査読有り 国際共著
T. Hayashi, S. Watanabe, T. Toda, K. Takeda, S. Toshniwal, K. Livescu
Proc. INTERSPEECH 頁: 4430 - 4434 2019年9月
-
Real-time neural text-to-speech with sequence-to-sequence acoustic model and WaveGlow or single Gaussian WaveRNN vocoders 査読有り
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. INTERSPEECH 頁: 1308 - 1312 2019年9月
-
Investigation of F0 conditioning and fully convolutional networks in variational autoencoder based voice conversion 査読有り 国際共著
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 頁: 709 - 713 2019年9月
-
Robustness of statistical voice conversion based on direct waveform modification against background sounds 査読有り
Y. Kurita, K. Kobayashi, K. Takeda, T. Toda
Proc. INTERSPEECH 頁: 684 - 688 2019年9月
-
Non-parallel voice conversion with cyclic variational autoencoder 査読有り
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. INTERSPEECH 頁: 674 - 678 2019年9月
-
Quasi-periodic WaveNet vocoder: a pitch dependent dilated convolution model for parametric speech generation 査読有り
Y.-C. Wu, T. Hayashi, P.L. Tobing, K. Kobayashi, T. Toda
Proc. INTERSPEECH 頁: 196 - 200 2019年9月
-
Refined WaveNet vocoder for variational autoencoder based voice conversion 査読有り 国際共著
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 頁: 5 pages 2019年9月
-
Generalized multichannel variational autoencoder for underdetermined source separation 査読有り
S. Seki, H. Kameoka, L. Li, T. Toda, K. Takeda
Proc. EUSIPCO 頁: 5 pages 2019年9月
-
Investigations of real-time Gaussian FFTNet and parallel WaveNet neural vocoders with simple acoustic features 査読有り
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP 頁: 7020 - 7024 2019年5月
-
Voice conversion with cyclic recurrent neural network and fine-tuned WaveNet vocoder 査読有り
P.L. Tobing, Y. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. IEEE ICASSP 頁: 6815 - 6819 2019年5月
-
Scene-dependent anomalous acoustic-event detection based on conditional WaveNet and i-Vector 査読有り
T. Komatsu, T. Hayashi, R. Kondo, T. Toda, K. Takeda
Proc. IEEE ICASSP 頁: 870 - 874 2019年5月
-
Environmental sound processing and its applications 招待有り 査読有り
K. Miyazaki, T. Toda, T. Hayashi, K. Takeda
IEEJ Transactions on Electronics, Information and Systems 14 巻 ( 3 ) 頁: 340 - 351 2019年3月
-
Speech-to-singing voice conversion: the challenges and strategies for improving vocal conversion processes 査読有り 国際共著
K. Vijayan, H. Li, T. Toda
IEEE Signal Processing Magazine 36 巻 ( 1 ) 頁: 95 - 102 2019年1月
-
An end-to-end model for cross-lingual transformation of paralinguistic information 査読有り
T. Kano, S. Takamichi, S. Sakti, G. Neubig, T. Toda, S. Nakamura
Machine Translation 32 巻 ( 4 ) 頁: 353 - 368 2018年12月
-
Back-translation-style data augmentation for end-to-end ASR 査読有り 国際共著
T. Hayashi, S. Watanabe, Y. Zhang, T. Toda, T. Hori, R. Astudillo, K. Takeda
Proc. IEEE SLT 頁: 426 - 433 2018年12月
-
Improving FFTNet vocoder with noise shaping and subband approaches 査読有り
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE SLT 頁: 304 - 311 2018年12月
-
An evaluation of deep spectral mappings and WaveNet vocoder for voice conversion 査読有り
P.L. Tobing, T. Hayashi, Y. Wu, K. Kobayashi, T. Toda
Proc. IEEE SLT 頁: 297 - 303 2018年12月
-
Daily activity recognition based on recurrent neural network using multi-modal signals 査読有り
A. Tamamori, T. Hayashi, T. Toda, K. Takeda
APSIPA Transactions on Signal and Information Processing 7 巻 ( e21 ) 頁: 1 - 11 2018年12月
-
Self-produced speech enhancement and suppression method using air- and body-conductive microphones 査読有り
M. Takada, S. Seki, T. Toda
Proc. APSIPA ASC 頁: 1240 - 1245 2018年11月
-
Connectionist temporal classification-based sound event encoder for converting sound events into onomatopoeia representations 査読有り
K. Miyazaki, T. Hayashi, T. Toda, K. Takeda
Proc. EUSIPCO 頁: 857 - 861 2018年9月
-
音声翻訳システムにおける音声変換の利用 招待有り
高道 慎之介, 戸田 智基
日本音響学会誌 74 巻 ( 9 ) 頁: 535 - 538 2018年9月
-
Designing a pneumatic bionic voice prosthesis - statistical approach for source excitation generation 査読有り 国際共著
F. Ahmadi, T. Toda
Proc. INTERSPEECH 頁: 3142 - 3146 2018年9月
-
Audio-visual voice conversion using deep canonical correlation analysis for deep bottleneck features 査読有り
S. Tamura, K. Horio, H. Endo, S. Hayamizu, T. Toda
Proc. INTERSPEECH 頁: 2469 - 2473 2018年9月
-
Frequency domain variants of velvet noise and their application to speech processing and synthesis 査読有り
H. Kawahara, K. Sakakibara, M. Morise, H. Banno, T. Toda, T. Irino
Proc. INTERSPEECH 頁: 2027 - 2031 2018年9月
-
Collapsed segment detection and reduction for WaveNet vocoder 査読有り
Y. Wu, K. Kobayashi, T. Hayashi, P.L. Tobing, T. Toda
Proc. INTERSPEECH 頁: 1998 - 1992 2018年9月
-
Multi-Head Decoder for end-to-end speech recognition 査読有り 国際共著
T. Hayashi, S. Watanabe, T. Toda, K. Takeda
Proc. INTERSPEECH 頁: 801 - 805 2018年9月
-
Anomalous sound event detection based on WaveNet 査読有り
T. Hayashi, T. Komatsu, R. Kondo, T. Toda, K. Takeda
Proc. EUSIPCO 頁: 2508 - 2512 2018年9月
-
Electrolarygeal speech enhancement with statistical voice conversion based on CLDNN 査読有り
K. Kobayashi, T. Toda
Proc. EUSIPCO 頁: 2129 - 2133 2018年9月
-
Stereophonic music separation based on non-negative tensor factorization with cepstral distance regularization 査読有り
S. Seki, T. Toda, K. Takeda
IEICE Transactions on Fundamentals E101-A 巻 ( 7 ) 頁: 1057 - 1064 2018年7月
-
A spoofing benchmark for the 2018 voice conversion challenge: leveraging from spoofing countermeasures for speech artifact assessment 査読有り 国際共著
T. Kinnunen, J. Lorenzo-Trueba, J. Yamagishi, T. Toda, D. Saito, F. Villavicencio, Z. Ling
Proc. Odyssey 2018 頁: 187 - 194 2018年6月
-
NU voice conversion system for the voice conversion challenge 2018 査読有り
P.L. Tobing, Y. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. Odyssey 2018 頁: 219 - 226 2018年6月
-
The NU non-parallel voice conversion system for the voice conversion challenge 2018 査読有り
Y. Wu, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda
Proc. Odyssey 2018 頁: 211 - 218 2018年6月
-
sprocket: open-source voice conversion software 査読有り
K. Kobayashi, T. Toda
Proc. Odyssey 2018 頁: 203 - 210 2018年6月
-
The voice conversion challenge 2018: promoting development of parallel and nonparallel methods 査読有り 国際共著
J. Lorenzo-Trueba, J. Yamagishi, T. Toda, D. Saito, F. Villavicencio, T. Kinnunen, Z. Ling
Proc. Odyssey 2018 頁: 195 - 202 2018年6月
-
Intra-gender statistical singing voice conversion with direct waveform modification using log-spectral differential 査読有り
K. Kobayashi, T. Toda, S. Nakamura
Speech Communication 99 巻 頁: 211 - 220 2018年5月
-
An investigation of subband WaveNet vocoder covering entire audible frequency range with limited acoustic features 査読有り
T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP 頁: 5654 - 5658 2018年4月
-
Development of "KamiRepo" system with automatic student identification to handle handwritten assignments on LMS 査読有り
S. Seiya, R. Ito, K. Okamoto, U. Tanikawa, S. Ohira, D. Deguchi, T. Toda
Proc. IEEE EDUCON 頁: 841 - 848 2018年4月
-
An investigation of noise shaping with perceptual weighting for WaveNet-based speech generation 査読有り
K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP 頁: 5664 - 5668 2018年4月
-
Deep neural network-based power spectrum reconstruction to improve quality of vocoded speech with limited acoustic parameters 査読有り
T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Acoustical Science and Technology, Acoustical Letter 39 巻 ( 2 ) 頁: 163 - 166 2018年3月
-
統計的声質変換ソフトウェア入門 招待有り 査読有り
戸田 智基, 小林 和弘
システム/制御/情報 62 巻 ( 2 ) 頁: 69 - 75 2018年2月
-
Daily activity recognition with large-scaled real-life recording datasets based on deep neural network using multi-modal signals 査読有り
T. Hayashi, M. Nishida, N. Kitaoka, T. Toda, K. Takeda
IEICE Transactions on Fundamentals E101-A 巻 ( 1 ) 頁: 199 - 210 2018年1月
-
Electrolaryngeal speech modification towards singing aid system for laryngectomees 査読有り
K. Morikawa, T. Toda
Proc. APSIPA ASC 頁: 1 - 4 2017年12月
-
Articulatory controllable speech modification based on statistical inversion and production mappings 査読有り
P.L. Tobing, K. Kobayashi, T. Toda
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 巻 ( 12 ) 頁: 2337 - 2350 2017年12月
-
An investigation of multi-speaker training for WaveNet vocoder 査読有り
T. Hayashi, A. Tamamori, K. Kobayashi, K. Takeda, T. Toda
Proc. IEEE ASRU 頁: 712 - 718 2017年12月
-
Subband WaveNet with overlapped single-sideband filterbanks 査読有り
T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ASRU 頁: 698 - 704 2017年12月
-
Accurate estimation of fo and aperiodicity based on periodicity detector residuals and deviations of phase derivatives 査読有り
H. Kawahara, K. Sakakibara, M. Morise, H. Banno, T. Toda
Proc. APSIPA ASC 頁: 1 - 9 2017年12月
-
An investigation of how to design control parameters for statistical voice timbre control 査読有り
K. Kubo, K. Kobayashi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. APSIPA ASC 頁: 1 - 4 2017年12月
-
Investigation of effectiveness on recurrent neural network for daily activity recognition using multi-modal signals 招待有り 査読有り
A. Tamamori, T. Hayashi, T. Toda, K. Takeda
Proc. APSIPA ASC 頁: 1 - 7 2017年12月
-
Deep acoustic-to-articulatory inversion mapping with latent trajectory modeling 査読有り
P.L. Tobing, H. Kameoka, T. Toda
Proc. APSIPA ASC 頁: 1 - 4 2017年12月
-
Duration-controlled LSTM for polyphonic sound event detection 査読有り 国際共著
T. Hayashi, S. Watanabe, T. Toda, T. Hori, J. Le Roux, K. Takeda
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 巻 ( 11 ) 頁: 2059 - 2070 2017年11月
-
Missing component restoration for masked speech signals based on time-domain spectrogram factorization 査読有り
S. Seki, H. Kameoka, T. Toda, K. Takeda.
Proc. IEEE MLSP 頁: 6 pages 2017年9月
-
A vibration control method of an electrolarynx based on statistical F0 pattern prediction 査読有り
K. Tanaka, T. Toda, S. Nakamura
IEICE Transactions on Information and Systems E100-D 巻 ( 9 ) 頁: 2165 - 2173 2017年9月
-
A modulation property of time-frequency derivatives of filtered phase and its application to aperiodicity and FO estimation 査読有り
H. Kawahara, K. Sakakibara, M. Morise, H. Banno, T. Toda
Proc. INTERSPEECH 頁: 424 - 428 2017年8月
-
Stereophonic music separation based on non-negative tensor factorization with cepstrum regularization 査読有り
S. Seki, T. Toda, K. Takeda
Proc. EUSIPCO 頁: 1011 - 1015 2017年8月
-
Speech enhancement using non-negative spectrogram models with mel-generalized cepstral regularization 査読有り
L. Li, H. Kameoka, T. Toda, S. Makino
Proc. INTERSPEECH 頁: 1998 - 2002 2017年8月
-
A new cosine series antialiasing function and its application to aliasing-free glottal source models for speech and singing synthesis 査読有り
H. Kawahara, K. Sakakibara, H. Banno, M. Morise, T. Toda, T. Irino
Proc. INTERSPEECH 頁: 1358 - 1362 2017年8月
-
Statistical voice conversion with WaveNet-based waveform generation 査読有り
K. Kobayashi, T. Hayashi, A. Tamamori, T. Toda
Proc. INTERSPEECH 頁: 1138 - 1142 2017年8月
-
Speaker-dependent WaveNet vocoder 査読有り
A. Tamamori, T. Hayashi, K. Kobayashi, K. Takeda, T. Toda
Proc. INTERSPEECH 頁: 1118 - 1122 2017年8月
-
Physically constrained statistical F0 prediction for electrolaryngeal speech enhancement 査読有り
K. Tanaka, H. Kameoka, T. Toda, S. Nakamura
Proc. INTERSPEECH 頁: 1069 - 1073 2017年8月
-
A noise suppression method for body-conducted soft speech based on non-negative tensor factorization of air- and body-conducted signals 査読有り
Y. Tajiri, H. Kameoka, T. Toda
Proc. IEEE ICASSP 頁: 4960 - 4964 2017年3月
-
Preserving word-level emphasis in speech-to-speech translation 査読有り
Q. Truong Do, T. Toda, G. Neubig, S. Sakti, S. Nakamura
IEEE/ACM Transactions on Audio, Speech and Language Processing 25 巻 ( 3 ) 頁: 544 - 556 2017年3月
-
BLSTM-HMM hybrid system combined with sound activity detection network for polyphonic sound event detection 査読有り 国際共著
T. Hayashi, S. Watanabe, T. Toda, T. Hori, J. Le Roux, K. Takeda
Proc. IEEE ICASSP 頁: 766 - 770 2017年3月
-
中間言語情報を記憶するピボット翻訳手法 査読有り
三浦 明波, Graham Neubig, Sakriani Sakti, 戸田 智基, 中村 哲
自然言語処理 23 巻 ( 5 ) 頁: 499 - 528 2016年12月
-
Non-native text-to-speech preserving speaker individuality based on partial correction of prosodic and phonetic characteristics 査読有り
Y. Oshima, S. Takamichi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
IEICE Transactions on Information and Systems E99-D 巻 ( 12 ) 頁: 3132 - 3139 2016年12月
-
F0 transformation techniques for statistical voice conversion with direct waveform modification with spectral differential 査読有り
K. Kobayashi, T. Toda, S. Nakamura
Proc. IEEE SLT 頁: 693 - 700 2016年12月
-
Learning cooperative persuasive dialogue policies using framing 査読有り
T. Hiraoka, G. Neubig, S. Sakti, T. Toda, S. Nakamura
Speech Communication 84 巻 頁: 83 - 96 2016年11月
-
Improvements of voice timbre control based on perceived age in singing voice conversion 査読有り
K. Kobayashi, T. Toda, T. Nakano, M. Goto, S. Nakamura
IEICE Transactions on Information and Systems E99-D 巻 ( 11 ) 頁: 2767 - 2777 2016年11月
-
A statistical sample-based approach to GMM-based voice conversion using tied-covariance acoustic models 査読有り
S. Takamichi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
IEICE Transactions on Information and Systems E99-D 巻 ( 10 ) 頁: 2490 - 2498 2016年10月
-
Investigation on recurrent neural network architectures for daily activity recognition 査読有り
A. Tamamori, T. Hayashi, T. Toda, K. Takeda
Proc. UV2016 頁: 1 - 4 2016年10月
-
Nonaudible murmur enhancement based on statistical voice conversion and noise suppression with external noise monitoring 査読有り
Y. Tajiri, T. Toda
Proc. 9th ISCA Speech Synthesis Workshop (SSW9) 頁: 54 - 60 2016年9月
-
Acoustic-to-articulatory inversion mapping based on latent trajectory Gaussian mixture model 査読有り
P.L. Tobing, T. Toda, H. Kameoka, S. Nakamura
Proc. INTERSPEECH 頁: 953 - 957 2016年9月
-
The Voice Conversion Challenge 2016 査読有り 国際共著
T. Toda, L.-H. Chen, D. Saito, F. Villavicencio, M. Wester, Z. Wu, J. Yamagishi
Proc. INTERSPEECH 頁: 1632 - 1636 2016年9月
-
The NU-NAIST voice conversion system for the Voice Conversion Challenge 2016 査読有り
K. Kobayashi, S. Takamichi, S. Nakamura, T. Toda
Proc. INTERSPEECH 頁: 1667 - 1671 2016年9月
-
Model integration for HMM- and DNN-based speech synthesis using Product-of-Experts framework 査読有り
K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. INTERSPEECH 頁: 2288 - 2292 2016年9月
-
A hybrid system for continuous word-level emphasis modeling based on HMM state clustering and adaptive training 査読有り
Q. Truong Do, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. INTERSPEECH 頁: 3196 - 3200 2016年9月
-
Removing noise from event-related potentials using a probabilistic generative model with grouped covariance matrices 査読有り
H. Maki, T. Toda, S. Sakti, G. Neubig, S. Nakamura
Proc. IEEE EMBC 頁: 1 - 4 2016年8月
-
Teaching social communication skills through human-agent interaction 査読有り
H. Tanaka, S. Sakti, G. Neubig, T. Toda, H. Negoro, H. Iwasaka, S. Nakamura
ACM Transactions on Interactive Intelligent Systems 6 巻 ( 2 ) 頁: 1 - 23 2016年8月
-
Bidirectional LSTM-HMM hybrid system for polyphonic sound event detection 査読有り 国際共著
T. Hayashi, S. Watanabe, T. Toda, T. Hori, J. Le Roux, K. Takeda
Proc. DCASE2016 workshop 頁: 1 - 5 2016年8月
-
Real-time vibration control of an electrolarynx based on statistical F0 contour prediction 査読有り
K. Tanaka, T. Toda, G. Neubig, S. Nakamura
Proc. EUSIPCO 頁: 1333 - 1337 2016年8月
-
Enhancing event-related potentials based on maximum a posteriori estimation with a spatial correlation prior 査読有り
H. Maki, T. Toda, S. Sakti, G. Neubig, S. Nakamura
IEICE Transactions on Information and Systems E99-D 巻 ( 6 ) 頁: 1410 - 1419 2016年6月
-
はじめての音声変換 招待有り
戸田 智基
日本音響学会誌 72 巻 ( 6 ) 頁: 324 - 331 2016年6月
-
Anti-spoofing for text-independent speaker verification: an initial database, comparison of countermeasures, and human performance 査読有り 国際共著
Z. Wu, P. De Leon, C. Demiroglu, A. Khodabakhsh, S. King, Z.-H. Ling, D. Saito, B. Stewart, T. Toda, M. Wester, J. Yamagishi
IEEE/ACM Transactions on Audio, Speech and Language Processing 24 巻 ( 4 ) 頁: 768 - 783 2016年4月
-
Post-filters to modify the modulation spectrum for statistical parametric speech synthesis 査読有り 国際共著
S. Takamichi, T. Toda, A.W. Black, G. Neubig, S. Sakti, S. Nakamura
IEEE/ACM Transactions on Audio, Speech and Language Processing 24 巻 ( 4 ) 頁: 755 - 767 2016年4月
-
Implementation of F0 transformation for statistical singing voice conversion based on direct waveform modification 査読有り
K. Kobayashi, T. Toda, S. Nakamura
Proc. IEEE ICASSP 頁: 5670 - 5674 2016年3月
-
An estimation method of voice timbre evaluation values using feature extraction with Gaussian mixture model based on reference singer 査読有り
S. Yamane, K. Kobayashi, T. Toda, T. Nakano, M. Goto, S. Nakamura
Proc. IEEE ICASSP 頁: 5265 - 5269 2016年3月
-
Statistical F0 prediction for electrolaryngeal speech enhancement considering generative process of F0 contours within product of experts framework 査読有り
K. Tanaka, H. Kameoka, T. Toda, S. Nakamura
Proc. IEEE ICASSP 頁: 5665 - 5669 2016年3月
-
Noise suppression method for body-conducted soft speech enhancement based on external noise monitoring 査読有り
Y. Tajiri, T. Toda, S. Nakamura
Proc. IEEE ICASSP 頁: 5935 - 5939 2016年3月
-
快適度推定に基づく用例ベース対話システム 査読有り
水上 雅博, Lasguido Nio, 木付 英士, 野村 敏男, Graham Neubig, 吉野 幸一郎, Sakriani Sakti, 戸田 智基, 中村 哲
人工知能学会論文誌 31 巻 ( 1 ) 頁: 1 - 12 2016年1月
-
Active learning for example-based dialog systems 査読有り
T. Hiraoka, G. Neubig, K. Yoshino, T. Toda, S. Nakamura
Proc. IWSDS 頁: 1 - 11 2016年1月
-
A dialog system to detect deception 査読有り
Y. Tsunomori, G. Neubig, T. Hiraoka, M. Mizukami, S. Sakti, T. Toda, S. Nakamura
Proc. IWSDS 頁: 1 - 6 2016年1月
-
機械翻訳システムの誤り分析のための誤り箇所選択手法 査読有り
赤部 晃一, Graham Neubig, Sakriani Sakti, 戸田 智基, 中村 哲
自然言語処理 23 巻 ( 1 ) 頁: 88 - 117 2016年1月
-
Improving translation of emphasis with pause prediction in speech-to-speech translation systems 査読有り
Q. Truong Do, S. Sakti, G. Neubig, T. Toda, S. Nakamura
Proc. IWSLT 頁: 204 - 208 2015年12月
-
Semantic parsing of ambiguous input through paraphrasing and verification 査読有り
P. Arthur, G. Neubig, S. Sakti, T. Toda, S. Nakamura
Transactions of the Association for Computational Linguistics 3 巻 頁: 571 - 584 2015年12月
-
Adaptive selection from multiple response candidates in example-based dialogue 査読有り
M. Mizukami, H. Kizuki, T. Nomura, G. Neubig, K. Yoshino, S. Sakti, T. Toda, S. Nakamura
Proc. IEEE ASRU 頁: 784 - 790 2015年12月
-
A study of social-affective communication: automatic prediction of emotion triggers and responses in television talk shows 査読有り
N. Lubis, S. Sakti, G. Neubig, K. Yoshino, T. Toda, S. Nakamura
Proc. IEEE ASRU 頁: 777 - 783 2015年12月
-
The NAIST ASR system for the 2015 Multi-Genre Broadcast Challenge: on combination of deep learning systems using a rank-score function 査読有り
Q. Truong Do, M. Heck, S. Sakti, G. Neubig, T. Toda, S. Nakamura
Proc. IEEE ASRU 頁: 654 - 659 2015年12月
-
Incremental sentence compression using LSTM recurrent networks 査読有り 国際共著
S. Sakti, F. Ilham, G. Neubig, T. Toda, Purwarianti, S. Nakamura
Proc. IEEE ASRU 頁: 252 - 258 2015年12月
-
Aliasing-free implementation of discrete-time glottal source models and their applications to speech synthesis and F0 extractor evaluation 査読有り
H. Kawahara, K. Sakakibara, H. Banno, M. Morise, T. Toda, T. Irino
Proc. APSIPA ASC 頁: 520 - 529 2015年12月
-
Learning to generate pseudo-code from source code using statistical machine translation 査読有り
Y. Oda, H. Fudaba, G. Neubig, H. Hata, S. Sakti, T. Toda, S. Nakamura
Proc. ASE 頁: 1 - 11 2015年11月
-
Pseudogen: a tool to automatically generate pseudo-code from source code 査読有り
H. Fudaba, Y. Oda, K. Akabe, G. Neubig, H. Hata, S. Sakti, T. Toda, S. Nakamura
Proc. ASE 頁: 1 - 6 2015年11月
-
An enhanced electrolarynx with automatic fundamental frequency control based on statistical prediction 査読有り
K. Tanaka, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. ASSETS 頁: 435 - 436 2015年10月
-
Construction and analysis of social-affective interaction corpus in English and Indonesian 査読有り
N. Lubis, S. Sakti, G. Neubig, T. Toda, S. Nakamura
Proc. O-COCOSDA 頁: 202 - 206 2015年10月
-
An investigation of machine translation evaluation metrics in cross-lingual question answering 査読有り
K. Sugiyama, M. Mizukami, G. Neubig, K. Yoshino, S. Sakti, T. Toda, S. Nakamur
Proc. 10th Workshop on Statistical Machine Translation 頁: 442 - 449 2015年9月
-
Preserving word-level emphasis in speech-to-speech translation using linear regression HSMMs 査読有り
D.Q. Truong, S. Takamichi, S. Sakti, G. Neubig, T. Toda, S. Nakamura
Proc. INTERSPEECH 頁: 3665 - 3669 2015年9月
-
Articulatory controllable speech modification based on Gaussian mixture models with direct waveform modification using spectrum differential 査読有り
P.L. Tobing, K. Kobayashi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. INTERSPEECH 頁: 3350 - 3354 2015年9月
-
Non-audible murmur enhancement based on statistical conversion using air- and body-conductive microphones in noisy environments 査読有り
Y. Tajiri, K. Tanaka, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. INTERSPEECH 頁: 2769 - 2773 2015年9月
-
Statistical singing voice conversion based on direct waveform modification with global variance 査読有り
K. Kobayashi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. INTERSPEECH 頁: 2754 - 2758 2015年9月
-
A latent variable model for joint pause prediction and dependency parsing 査読有り
T.T. Nguyen, G. Neubig, H. Shindo, S. Sakti, T. Toda, S. Nakamura
Proc. INTERSPEECH 頁: 2719 - 2723 2015年9月
-
Speed or accuracy? a study in evaluation of simultaneous speech translation 査読有り
T. Mieno, G. Neubig, S. Sakti, T. Toda, S. Nakamura
Proc. INTERSPEECH 頁: 2267 - 2271 2015年9月
-
Modulation spectrum-constrained trajectory training algorithm for HMM-based speech synthesis 査読有り 国際共著
S. Takamichi, T. Toda, A.W. Black, S. Nakamura
Proc. INTERSPEECH 頁: 1206 - 1210 2015年9月
-
Non-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics 査読有り
Y. Oshima, S. Takamichi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. INTERSPEECH 頁: 299 - 303 2015年9月
-
The NAIST text-to-speech system for the Blizzard Challenge 2015 査読有り
S. Takamichi, K. Kobayashi, K. Tanaka, T. Toda, S. Nakamura
Proc. Blizzard Challenge Workshop 頁: 1 - 4 2015年9月
-
Prosody-controllable HMM-based speech synthesis using speech input 査読有り
Y. Nishigaki, S. Takamichi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. MLSLP 頁: 1 - 5 2015年9月