Nose Takashi

ノセタカシ | Nose Takashi

Affiliation and department：
Job title： Associate Professor
Homepage URL (2)： http://db.tohoku.ac.jp/whois/detail/ceb054ce70c91a3165ec32dd6a60d038.html , http://db.tohoku.ac.jp/whois/e_detail/ceb054ce70c91a3165ec32dd6a60d038.html

Research field (2)： Intelligent robotics , Perceptual information processing

Research keywords (7)：マルチメディア情報処理 , 音楽情報処理 , 音声符号化 , 音声対話 , 音声認識 , 音声合成 , 音声情報処理

Research theme for competitive and other funds (16)：

2021 - 2026 Development of a virtual classmate for assistance of online course
2022 - 2025 話者・地域・スタイルモーフィング音声合成による実環境リスニング学習支援
2017 - 2021 Research and development of multi-modal interactive English learning system based on deep learning
2016 - 2019 Research and development of a Japanese pronunciation training system using average voice morphing
2016 - 2018 Study on new vocal design focusing on naturally dehumanized singing

Show all

Papers (147)：

Xuecheng Niu, Akinori Ito, Takashi Nose. Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning. 2024
Simon Jolibois, Akinori Ito, Takashi Nose. Multimodal Expressive Embodied Conversational Agent Design. Communications in Computer and Information Science. 2023. 244-249
Yuki Fukazawa, Akinori Ito, Takashi Nose. Effect of Data Size and Machine Translation on the Accuracy of Automatic Personality Classification. Advances in Intelligent Information Hiding and Multimedia Signal Processing. 2023. 405-413
Ryota Yahagi, Akinori Ito, Takashi Nose, Yuya Chiba. Response Sentence Modification Using a Sentence Vector for a Flexible Response Generation of Retrieval-based Dialogue Systems. 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 2022
Daisuke Horii, Akinori Ito, Takashi Nose. Design and Construction of Japanese Multimodal Utterance Corpus with Improved Emotion Balance and Naturalness. 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 2022

ｍore...

MISC (52)：

Invited Talk : Synthesis, Recognition and Conversion of Various Speech Using Deep Learning and Their Applications. 2017. 117. 160. 3-8
A Study on DNN-Based Speech Synthesis Using Vector Quantization of Spectral Features. 2017. 116. 414. 65-70
Poster Presentation : A Study on Singer-Independent Singing Voice Conversion Using Read Speech Based on Neural Network. 2017. 116. 414. 17-22
Improvement of Accent Sandhi Rules Based on Accent Dictionary for Japanese Text-to-Speech Systems. 2016. 116. 378. 31-36
Poster Presentation : Development of the Julius-compatible interface for the speech recognition engine of Kaldi toolkit. 2016. 116. 378. 49-51

ｍore...

Books (3)：

Education (1)：

- 2009 Tokyo Institute of Technology Graduate School, Division of Integrated Science and Engineering 物理情報システム専攻

Professional career (1)：

Committee career (4)：

Association Membership(s) (5)：

ISCA , 情報処理学会 , 音響学会 , 電子情報通信学会 , IEEE

※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page