Rchr
J-GLOBAL ID：201601020716345755
Update date: Aug. 21, 2024
Koriyama Tomoki
コオリヤマ トモキ | Koriyama Tomoki
Affiliation and department：
Job title：
助教
Research field (1)：
Perceptual information processing
Research theme for competitive and other funds (6)：
- 2021 - 2024 Speech Processing Based on Deep Gaussian Process With Stochastic Differential Equation Layers
- 2019 - 2022 A Study of Deep Gaussian Process Based Statistcal Speech Synthesis
- 2017 - 2020 A Study on Prosody Embedding Based on Gaussain Proceess Latent Variable Model
- 2015 - 2018 Establishment of speech synthesis framework based on Gaussian process regression
- 2013 - 2015 Research on speech synthesis using non-parametric modeling based on Gaussian process regression
- 2012 - 2015 Research on advanced robust speech synthesis and its applications to multi-lingual speech communication
Show all
Papers (47)：
-
Xuan Luo, Shinnosuke Takamichi, Yuki Saito, Tomoki Koriyama, Hiroshi Saruwatari. Emotion-controllable Speech Synthesis Using Emotion Soft Label, Utterance-level Prosodic Factors, and Word-level Prominence. APSIPA Transactions on Signal and Information Processing. 2024. 13. 1
-
Dong Yang, Tomoki Koriyama, Yuki Saito, Takaaki Saeki, Detai Xin, Hiroshi Saruwatari. Duration-Aware Pause Insertion Using Pre-Trained Language Model for Multi-Speaker Text-To-Speech. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2023
-
Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, Yuki Saito, Yusuke Ijima, Ryo Masumura, Hiroshi Saruwatari. Predicting VQVAE-based Character Acting Style from Quotation-Annotated Text for Audiobook Speech Synthesis. INTERSPEECH. 2022. 4551-4555
-
Kentaro Mitsui, Tomoki Koriyama, Hiroshi Saruwatari. Deep Gaussian process based multi-speaker speech synthesis with latent speaker representation. Speech Communication. 2021. 132. 132-145
-
Taiki Nakamura, Tomoki Koriyama, Hiroshi Saruwatari. Sequence-to-sequence learning for deep Gaussian process based speech synthesis using self-attention GP layer. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2021. 5. 3621-3625
ｍore...
MISC (16)：
-
中田亘, 郡山知樹, 高道慎之介, 齋藤佑樹, 井島勇祐, 増村亮, 猿渡洋. Audiobook Speech Synthesis based on Character embedding for Distinguishable Character Acting. 日本音響学会研究発表会講演論文集(CD-ROM). 2022. 2022
-
中田亘, 郡山知樹, 高道慎之介, 齋藤佑樹, 井島勇祐, 増村亮, 猿渡洋. Multi-speaker Audiobook Speech Synthesis using Discrete Character Acting Styles Acquired by VQVAE. 電子情報通信学会技術研究報告(Web). 2021. 121. 281(NLC2021 18-27)
-
The Effectiveness of Additional Context in DNN-based Spontaneous Speech Synthesis. 2020. 119. 440. 65-70
-
高道慎之介, 小沼海, 金田卓, 金田隆志, 齋藤佑樹, 郡山知樹, 猿渡洋. Crowdsourcing-based parameter optimization for frequency warping-based speaker anonymization. 日本音響学会研究発表会講演論文集(CD-ROM). 2020. 2020
-
高道慎之介, 齋藤佑樹, 中村友彦, 郡山知樹, 猿渡洋. manga2voice: speech analysis towards audio synthesis from comic image. 日本音響学会研究発表会講演論文集(CD-ROM). 2020. 2020
ｍore...
Work history (2)：
- 2019/04 - 現在 The University of Tokyo Center for Education and Research in Information Science and Technology (CERIST), Graduate School of Information Science and Technology / Mathematics and Informatics Center Assistant Professor
- 2014/09 - 2019/03 Tokyo Institute of Technology School of Engineering Assistant Professor
Return to Previous Page
