論文 - 戸田 智基
-
Speaker-aware multi-task learning for speech emotion recognition 査読有り 国際共著 Open Access
X. Shi, X. Li, T. Toda
Proc. INTERSPEECH 頁： 4333 - 4337 2025年8月
-
Advancing emotion recognition via ensemble learning: integrating speech, context, and text representations 査読有り 国際共著 Open Access
X. Shi, J. Mi, X. Li, T. Toda
Proc. INTERSPEECH 頁： 4693 - 4697 2025年8月
-
Comparative analysis of fast and high-fidelity neural vocoders for low-latency streaming synthesis in resource-constrained environments 査読有り Open Access
R. Yoneyama, M. Kawamura, R. Terashima, R. Yamamoto, T. Toda
Proc. INTERSPEECH 頁： 4888 - 4892 2025年8月
-
Who, When, and What: leveraging the "Three Ws" concept for emotion recognition in conversation 査読有り 国際共著 Open Access
X. Shi, X, Li, T. Toda
Proc. INTERSPEECH 頁： 1763 - 1767 2025年8月
-
GST-BERT-TTS: prosody prediction without accentual labels for multi-speaker TTS using BERT with global style tokens 査読有り Open Access
T. Ogura, T. Okamoto, Y. Ohtani, E. Cooper, T. Toda, H. Kawai
Proc. INTERSPEECH 頁： 444 - 448 2025年8月
-
Improving electrolaryngeal speech enhancement via a representation learning method based on integrated text and speech representations 査読有り 国際共著
D. Ma, J. Mi, F. Li, L.P. Violeta, K. Kobayashi, T. Toda
Proc. IEEE EMBC 頁： 6 pages 2025年7月
-
Phoneme-level duration controllable neural text-to-speech with phoneme embedding skip connection and modified Gaussian duration modeling 査読有り Open Access
T. Ogura, T. Okamoto, Y. Ohtani, E. Cooper, T. Toda, H. Kawai
IEEE Access 13 巻 頁： 118369 - 118380 2025年7月
-
Learning separated representations for instrument-based music similarity 査読有り Open Access
Y. Hashizume, L. Li, A. Miyashita, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 1, e16 ) 頁： 1 - 32 2025年7月
-
Pretraining and fine-tuning techniques for electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion 査読有り Open Access
D. Ma, L.P. Violeta, K. Kobayashi, T. Toda
IEEE Transactions on Audio, Speech and Language Processing 33 巻 頁： 3189 - 3201 2025年7月
-
Noise and reverberation-controllable voice conversion 査読有り Open Access
Y. Choi, C. Xie, T. Toda
IEEE Transactions on Audio, Speech and Language Processing 33 巻 頁： 2430 - 2443 2025年6月
-
PMF-CEC: phoneme-augmented multimodal fusion for context-aware ASR error correction with error-specific selective decoding 査読有り Open Access
J. He, T. Toda
IEEE Transactions on Audio, Speech and Language Processing 33 巻 頁： 2402 - 2417 2025年6月
-
Improving anomalous sound detection through pseudo-anomalous set selection and pseudo-label utilization under unlabeled conditions 査読有り Open Access
I. Kuroyanagi, T. Fujimura, K. Takeda, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 1, e13 ) 頁： 1 - 28 2025年6月
-
Analysis and extension of noisy-target training for unsupervised target signal enhancement 査読有り Open Access
T. Fujimura, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 1, e12 ) 頁： 1 - 27 2025年6月
-
An investigation of noisy-to-noisy voice conversion performance in various noisy conditions 査読有り Open Access
C. Xie, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 1, e10 ) 頁： 1 - 30 2025年6月
-
Resolving domain mismatches in electrolaryngeal speech enhancement with linguistic intermediates 査読有り
L.P. Violeta, W.-C. Huang, D. Ma, R. Yamamoto, K. Kobayashi, T. Toda
IEEE Journal of Selected Topics in Signal Processing 19 巻 ( 5 ) 頁： 827 - 839 2025年6月
-
Sequence-to-sequence voice conversion-based techniques for electrolaryngeal speech enhancement in noisy and reverberant conditions 査読有り 国際共著 Open Access
D. Ma, Y. Choi, T. Fujimura, F. Li, C. Xie, K. Kobayashi, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 1, e8 ) 頁： 1 - 40 2025年5月
-
Fast neural vocoder with fundamental frequency control using finite impulse response filters 査読有り Open Access
Y. Ohtani, T. Okamoto, T. Toda, H. Kawai
IEEE Transactions on Audio, Speech and Language Processing 33 巻 頁： 1893 - 1906 2025年4月
-
Predicting fundamental frequency patterns in electrolaryngeal speech using automated phoneme extraction 査読有り Open Access
M. Eshghi, T. Toda
IEEE Access 13 巻 頁： 73831 - 73847 2025年4月
-
Generalized sound field interpolation for freely spaced microphone arrays in rotation-robust beamforming 査読有り Open Access
S. Luan, Y. Wakabayashi, T. Toda
Applied Acoustics 236 巻 ( Article 110706 ) 頁： 1 - 15 2025年4月
-
Mora-level prosody prediction for text-to-speech using Japanese BERT without accentual labels 査読有り
T. Ogura, T. Okamoto, Y. Ohtani, E. Cooper, T. Toda, H. Kawai
Proc. IEEE ICASSP 頁： 1 - 5 2025年4月