Tomoki Koriyama
Tomoki Koriyama
The University of Tokyo
確認したメール アドレス: なし - ホームページ
タイトル
引用先
引用先
Statistical parametric speech synthesis based on Gaussian process regression
T Koriyama, T Nose, T Kobayashi
IEEE journal of selected topics in Signal Processing 8 (2), 173-183, 2013
522013
JVS corpus: free Japanese multi-speaker voice corpus
S Takamichi, K Mitsui, Y Saito, T Koriyama, N Tanji, H Saruwatari
arXiv preprint arXiv:1908.06248, 2019
222019
On the use of extended context for HMM-based spontaneous conversational speech synthesis
T Koriyama, T Nose, T Kobayashi
Twelfth Annual Conference of the International Speech Communication Association, 2011
202011
Sampling-based speech parameter generation using moment-matching networks
S Takamichi, T Koriyama, H Saruwatari
arXiv preprint arXiv:1704.03626, 2017
192017
Prosodic variation enhancement using unsupervised context labeling for HMM-based expressive speech synthesis
Y Maeno, T Nose, T Kobayashi, T Koriyama, Y Ijima, H Nakajima, ...
Speech Communication 57, 144-154, 2014
142014
HMM-based expressive singing voice synthesis with singing style control and robust pitch modeling
T Nose, M Kanemoto, T Koriyama, T Kobayashi
Computer Speech & Language 34 (1), 308-322, 2015
132015
Prosody generation using frame-based Gaussian process regression and classification for statistical parametric speech synthesis
T Koriyama, T Kobayashi
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
132015
Conversational spontaneous speech synthesis using average voice model
T Koriyama, T Nose, T Kobayashi
Eleventh Annual Conference of the International Speech Communication Association, 2010
132010
Statistical parametric speech synthesis using deep Gaussian processes
T Koriyama, T Kobayashi
IEEE/ACM Transactions on Audio, Speech, and Language Processing 27 (5), 948-959, 2019
122019
Parametric speech synthesis based on Gaussian process regression using global variance and hyperparameter optimization
T Koriyama, T Nose, T Kobayashi
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
122014
Speech emotion recognition using convolutional long short-term memory neural network and support vector machines
N Kurpukdee, T Koriyama, T Kobayashi, S Kasuriya, C Wutiwiwatchai, ...
2017 Asia-Pacific Signal and Information Processing Association Annual …, 2017
112017
IEICE technical report
T Asai, T Tsurumaru
ISEC2010-121 (in Japanese), 2011
11*2011
Duration prediction using multiple Gaussian process experts for GPR-based speech synthesis
D Moungsri, T Koriyama, T Kobayashi
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
92017
A comparison of speech synthesis systems based on GPR, HMM, and DNN with a small amount of training data
T Koriyama, T Kobayashi
Sixteenth Annual Conference of the International Speech Communication …, 2015
82015
Frame-level acoustic modeling based on Gaussian process regression for statistical nonparametric speech synthesis
T Koriyama, T Nose, T Kobayashi
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
82013
Statistical nonparametric speech synthesis using sparse Gaussian processes.
T Koriyama, T Nose, T Kobayashi
INTERSPEECH, 1072-1076, 2013
82013
An F0 modeling technique based on prosodic events for spontaneous speech synthesis
T Koriyama, T Nose, T Kobayashi
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
82012
HMM-based Thai speech synthesis using unsupervised stress context labeling
D Moungsri, T Koriyama, T Kobayashi
Signal and Information Processing Association Annual Summit and Conference …, 2014
72014
A style control technique for singing voice synthesis based on multiple-regression HSMM.
T Nose, M Kanemoto, T Koriyama, T Kobayashi
INTERSPEECH, 378-382, 2013
72013
Generative moment matching network-based random modulation post-filter for DNN-based singing voice synthesis and neural double-tracking
H Tamaru, Y Saito, S Takamichi, T Koriyama, H Saruwatari
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
62019
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20