論文 - 戸田 智基
-
A preliminary study on sectional voice anonymization and detection 査読有り 国際共著
S. Tang, Z. Liu, L. Chen, K. Lee, T. Toda, Z.-H. Ling
Proc. APSIPA ASC 頁: 318 - 323 2025年10月
-
Hierarchical symbolic music generation with variational autoencoder-based bar-wise feature sequences 査読有り
K. Sawada, W.-C. Huang, T. Toda
Proc. APSIPA ASC 頁: 299 - 304 2025年10月
-
Adjusting bias in anomaly scores via variance minimization for domain-generalized discriminative anomalous sound detection 査読有り
M. Matsumoto, T. Fujimura, W.-C. Huang, T. Toda
Proc. DCASE Workshop 頁: 25 - 29 2025年10月
-
ASDKit: a toolkit for comprehensive evaluation of anomalous sound detection methods 査読有り 国際共著
T. Fujimura, K. Wilkinghoff, K. Imoto, T. Toda
Proc. DCASE Workshop 頁: 40 - 44 2025年10月
-
Discriminative anomalous sound detection using pseudo labels, target signal enhancement, and ensemble feature extractors 査読有り
T. Fujimura, I. Kuroyanagi, T. Toda
Proc. DCASE Workshop 頁: 180 - 184 2025年10月
-
Music similarity representation learning focusing on individual instruments with source separation and human preference 査読有り
T. Imamura, Y. Hashizume, W.-C. Huang, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 4, e305 ) 頁: 1 - 29 2025年10月
-
喉頭摘出者における自己音声の再獲得 ~Save the Voice Project~ 査読有り
西尾 直樹, 小林 和弘, 戸田 智基
気管食道科学会会報 76 巻 ( 5 ) 頁: 255 - 263 2025年10月
-
VAE-SiFiGAN: source-filter HiFi-GAN based on variational autoencoder representations with enhanced pitch controllability 査読有り Open Access
K. Ogita, R. Yoneyama, W.-C. Huang, T. Toda
Proc. EUSIPCO 頁: 531 - 535 2025年9月
-
QHARMA-GAN: quasi-harmonic neural vocoder based on autoregressive moving average model 査読有り Open Access
S. Chen, T. Toda
IEEE Transactions on Audio, Speech and Language Processing 33 巻 頁: 3703 - 3719 2025年9月
-
Automatic design optimization of preference-based subjective evaluation with online learning in crowdsourcing environment 査読有り Open Access
Y. Yasuda, T. Toda
Computer Speech and Language 96 巻 ( Article 101888 ) 頁: 1 - 16 2025年9月
-
Serenade: a singing style conversion framework based on audio infilling 査読有り Open Access
L.P. Violeta, W.-C. Huang, T. Toda
Proc. EUSIPCO 頁: 411 - 415 2025年9月
-
M4SER: multimodal, multirepresentation, multitask, and multistrategy learning for speech emotion recognition 査読有り 国際共著
J. He, X. Shi, C.-H. Hu, J. Mi, X. Li, T. Toda
IEEE Transactions on Audio, Speech and Language Processing 33 巻 頁: 4055 - 4070 2025年9月
-
Text- and speech-style control for lecture speech generation focusing on disfluency 査読有り
D. Yoshioka, Y. Nakata, Y. Yasuda, T. Toda
APSIPA Transactions on Signal and Information Processing 14 巻 ( 1, e26 ) 頁: 1 - 31 2025年9月
-
Continual subjective evaluation method of speech by merging sort-based preference tests towards ever-expanding corpus of human ratings 査読有り Open Access
Y. Yasuda, J. Yamagishi, T. Toda
Proc. SSW 頁: 14 - 20 2025年8月
-
Eigenvoice synthesis based on model editing for speaker generation 査読有り Open Access
M. Murata, K. Miyazaki, T. Koriyama, T. Toda
Proc. INTERSPEECH 頁: 5523 - 5527 2025年8月
-
Unifying listener scoring scales: comparison learning framework for speech quality assessment and continuous speech emotion recognition 査読有り Open Access
C.-H. Hu, Y. Yasuda, A. Yoshimoto, T. Toda
Proc. INTERSPEECH 頁: 5428 - 5432 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
-
SHEET: a multi-purpose open-source speech human evaluation estimation toolkit 査読有り Open Access
W.-C. Huang, E. Cooper, T. Toda
Proc. INTERSPEECH 頁: 2355 - 2359 2025年8月
-
CMT-LLM: context-aware multi-talker ASR utilizing large language models 査読有り Open Access
J. He, N. Sawada, K. Miyazaki, T. Toda
Proc. INTERSPEECH 頁: 2575 - 2579 2025年8月
-
GIA-MIC: multimodal emotion recognition with gated interactive attention and modality-invariant learning constraints 査読有り Open Access
J. He, J. Mi, T. Toda
Proc. INTERSPEECH 頁: 2695 - 2699 2025年8月