Yukiya Hono

Visiting Assistant Professor at Nagoya Institute of Technology

English page Japanese page

Profile

Research and Work Experiences

May. 2022 -- Present
Visiting Assistant Processor at Nagoya Institute of Technology
Apr. 2022 -- Present
Full Time Employee at rinna Co., Ltd., Japan
Apr. 2022 -- Apr. 2022
Researcher at Nagoya Institute of Technology
Jan. 2020 -- Feb. 2020
Visiting Researcher at University of Sheffield, U.K.
Oct. 2019 -- Dec. 2019
Visiting Researcher at University of Edinburgh, U.K.
July. 2019 -- Aug. 2019
Internship at Microsoft Development Co., Ltd., Japan

Educations

Apr. 2019 -- Mar. 2022
Department of Computer Science, Nagoya Institute of Technology, Japan (PhD)
Apr. 2017 -- Mar. 2019
Department of Computer Science, Nagoya Institute of Technology, Japan (Master)
Apr. 2013 -- Mar. 2017
Department of Computer Science, Nagoya Institute of Technology, Japan (Bachelor)

Awards

5 Sep. 2024
The 3rd Yoshida Prize Speech Synthesis Researcher Award, Acoustical Society of Japan
9 Dec. 2023
IEEE Nagoya Section Young Researcher Award 2023
27 Dec. 2022
2022 IEEE Signal Processing Society Japan Student Journal Paper Award
15 Sep. 2022
The 52nd Awaya Prize Young Researcher Award, Acoustical Society of Japan
26 Mar. 2022
IEEE Nagoya Section Conference Presentation Award 2022
24 Mar. 2022
The Vice President Award, Nagoya Institute of Technology
28 Dec. 2021
2021 IEEE Signal Processing Society Japan Student Conference Paper Award
23 Mar. 2021
IEEE Nagoya Section Excellent student Award 2020
11 June 2019
IEICE Tokai Section Student Award 2018
06 Mar. 2019
The 18th Student Presentation Award, Acoustical Society of Japan
18 Dec. 2018
2018 the presentation excellence prize from ASJ-Tokai
04 Aug. 2018
Overview Lecture Award, 22nd Tokai region's speech related master's graduation thesis midterm presentation event
23 Mar. 2017
DEN'EIKAI Award

Software

Apr. 2018 -- Present
HMM/DNN-based Singing Voice Synthesis System (Sinsy)

Resarch Topics

Text-to-speech synthesis
Singing voice synthesis

Society

Institute of Electrical and Electronics Engineers (IEEE)
Acoustical Society of Japan (ASJ)

Publications

Journal Paper

  • PeriodNet: A non-autoregressive raw waveform generative model with a structure separating periodic and aperiodic components

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    IEEE Access, vol. 9, pp. 137599-137612, October, 2021. (DOI: 10.1109/ACCESS.2021.3118033) (IEEE Xplore) (demo page)

  • Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 2803-2815, August, 2021. (DOI: 10.1109/TASLP.2021.3104165) (IEEE SPS Japan Student Journal Paper Award) (IEEE Xplore) (demo page)

International Conference

  • PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems

    Kentaro Mitsui, Koh Mitsuda, Toshiaki Wakatsuki, Yukiya Hono, and Kei Sawada

    Findings of the Association for Computational Linguistics EMNLP 2024. (accepted) (arXiv preprint)

  • Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition

    Yukiya Hono, Koh Mitsuda, Tianyu Zhao, Kentaro Mitsui, Toshiaki Wakatsuki, and Kei Sawada

    Findings of the Association for Computational Linguistics ACL 2024, pp. 13289-13305, Bangkok, Thailand, August 2024. (ACL Anthology)

  • Release of Pre-Trained Models for the Japanese Language

    Kei Sawada, Tianyu Zhao, Makoto Shing, Kentaro Mitsui, Akio Kaga, Yukiya Hono, Toshiaki Wakatsuki, and Koh Mitsuda

    2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 13898-13905, Torino, Italia, May, 2024. (ACL Anthology)

  • PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model

    Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 12782-12786, Seoul, Korea, April, 2024. (IEEE Xplore)

  • UniFLG: Unified Facial Landmark Generator from Text or Speech

    Kentaro Mitsui, Yukiya Hono, and Kei Sawada

    Interspeech 2023, pp. 5501-5505, Dublin, Ireland, September, 2023. (ISCA Archive)

  • Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism

    Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, June, 2023. (IEEE Xplore)

  • Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural Speech Synthesis System

    Takenori Yoshimura, Shinji Takaki Kazuhiro Nakamura, Keiichiro Oura, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, June, 2023. (IEEE Xplore)

  • End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue

    Kentaro Mitsui, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, and Keiichi Tokuda

    Interspeech 2022, pp. 2328–2332, Incheon, Korea, September, 2022. (ISCA Archive)

  • PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6049-6053, Toronto, Ontario, Canada, June, 2021. (IEEE SPS Japan Student Conference Paper Award) (IEEE Xplore)

  • Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis

    Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Interspeech 2020, pp. 3441-3445, Shanghai, China, October, 2020. (ISCA archive)

  • Singing voice synthesis based on generative adversarial networks

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6955-6959, Brighton, UK, May, 2019.

  • Singing Voice Conversion Using Posted Waveform Data on Music Social Media

    Koki Senda, Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1913-1917, Honolulu, Hawaii, November, 2018.

  • Recent Development of the DNN-based Singing Voice Synthesis System -- Sinsy

    Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1003-1009, Honolulu, Hawaii, November, 2018.

Technical Report

  • Singing voice synthesis based on a frame-driven attention mechanism considering vocal timing deviation

    Miku Nishihara, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Technical Report of IEICE, vol. 122, no. 339, pp. 19-24, Okinawa, Japan, February, 2023.

  • A comparison of neural vocoders in singing voice synthesis

    Sota Wada, Yukiya Hono, Shinji Takaki, Keiichiro Oura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Technical Report of IEICE, vol. 119, no. 321, pp. 85-90, Tokyo, Japan, December, 2019.

Domestic Conference

  • Consideration on periodic excitation signals in source-filter type neural vocoders

    Hikaru Aohara, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2024 Spring Meeting, pp. 813-816, Tokyo, Japan, March, 2024. (Student presentation award)

  • Generating Spoken Dialogue from Text for Natural Conversations Between AI Agents

    Kentaro Mitsui, Yukiya Hono, Kei Sawada

    Acoustical Society of Japan 2024 Spring Meeting, pp. 1327-1330, Tokyo, Japan, March, 2024.

  • End-to-end speech recognition by integrating self-supervised speech and language model

    Yukiya Hono, Koh Mitsuda, Tianyu Zhao, Kentaro Mitsui, Toshiaki Wakatsuki, Kei Sawada

    Acoustical Society of Japan 2024 Spring Meeting, pp. 1323-1326, Tokyo, Japan, March, 2024.

  • Japanese pre-trained models using self-supervised learning and their applications to speech recognition and synthesis

    Kei Sawada, Yukiya Hono, Kentaro Mitsui

    Acoustical Society of Japan 2024 Spring Meeting, pp. 1319-1320, Tokyo, Japan, March, 2024. (Invited talk)

  • A neural vocoder training method using a pitch extractor for fundamental frequency controllabilit

    Shion Fukuda, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2023 Autumn Meeting, pp. 1065-1068, Aichi, Japan, September, 2023.

  • A neural vocoder training method using a pitch extractor for fundamental frequency controllabilit

    Shion Fukuda, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda,

    Acoustical Society of Japan 2023 Autumn Meeting, pp. 1065-1068, Aichi, Japan, September, 2023.

  • Neural vocoder based on disentangled representation learning to control fundamental frequency

    Suzuka Sato, Takato Fujimoto, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2023 Autumn Meeting, pp. 1061-1064, Aichi, Japan, September, 2023.

  • PeriodGrad: A neural vocoder based on a diffusion probabilistic model with fundamental frequency controllability

    Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda,

    Acoustical Society of Japan 2023 Autumn Meeting, pp. 1045-1048, Aichi, Japan, September, 2023.

  • A study on vocal timing modeling for sequence-to-sequence singing voice synthesis

    Miku Nishihara, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2022 Autumn Meeting, pp. 1359-1362, Hokkaido, Japan, September, 2022.

  • Text-to-speech synthesis based on the extraction and prediction of latent speaking style representation using spontaneous dialogue

    Kentaro Mitsui, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2022 Autumn Meeting, pp. 1593-1596, Hokkaido, Japan, September, 2022.

  • A study on musical note position-aware attention mechanism for sequence-to-sequence singing voice synthesis

    Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2022 Autumn Meeting, pp. 1589-1592, Hokkaido, Japan, September, 2022.

  • Embedding a differentiable mel-cepstral synthesis filter to an end-to-end speech synthesis system

    Takenori Yoshimura, Shinji Takaki, Kazuhiro Nakamura, Keiichiro Oura, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2022 Autumn Meeting, pp. 1585-1588, Hokkaido, Japan, September, 2022.

  • Neural vocoder training considering the aperiodic measure

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Kazuhiro Nakamura, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2022 Spring Meeting, pp. 973-976, Japan, March, 2022. (Awaya Prize Young Researcher Award)

  • Sequence-to-sequence singing voice synthesis considering vocal timing fluctuation

    Yukiya Hono, Taisei Kato, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2021 Autumn Meeting, pp. 911-914, Japan, September, 2021.

  • Automatic pitch correction of tuneless singing for DNN-based singing voice synthesis

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2021 Autumn Meeting, pp. 907-910, Japan, September, 2021.

  • An investigation of modeling speech waveform by neural vocoder based on periodic/aperiodic decomposition

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2021 Spring Meeting, pp. 861-864, Japan, March, 2021.

  • Expressive speech synthesis using hierarchical multi-grained generative model

    Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2020 Autumn Meeting, pp. 791-794, Japan, September, 2020.

  • An investigation of modeling periodic and aperiodic components in speech vocoder based on deep neural networks

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2020 Autumn Meeting, pp. 759-760, Japan, September, 2020.

  • Statistical parametric speech synthesis based on acoustic parameter prediction using cascade model architecture

    Kentaro Mitsui, Yukiya Hono, Kazuna Tsuboi, Kei Sawada

    Acoustical Society of Japan 2020 Spring Meeting, pp. 1107-1108, Saitama, Japan, March, 2020.

  • A study on singing voice synthesis with attention mechanism using musical score time information

    Shumma Murata, Takato Fujimoto, Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2019 Autumn Meeting, pp. 943-944, Shiga, Japan, September, 2019.

  • AI Singer Rinna: a singing voice synthesis system using user's singing voice or musical score

    Kei Sawada, Kazuna Tsuboi, Xianchao Wu, Zhan Chen, Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2019 Spring Meeting, pp. 1041-1044, Tokyo, Japan, March, 2019.

  • Singing voice synthesis using generative adversarial networks

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2019 Spring Meeting, pp. 1039-1040, Tokyo, Japan, March, 2019.

  • A DNN-based singing voice synthesis system -- Sinsy

    Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2018 Autumn Meeting, pp. 1099-1102, Oita, Japan, September, 2018. (Student presentation award)

  • Singing voice synthesis based on neural network using a structure of a hidden semi-Markov model

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Acoustical Society of Japan 2018 Spring Meeting, pp. 247-248, Saitama, Japan, March, 2018.

  • Singing voice conversion using post data in music SNS

    Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Daisuke Kondo, and Daisuke Ishikawa

    Acoustical Society of Japan 2017 Autumn Meeting, pp. 209-210, Ehime, Japan, September, 2017.

Thesis

  • Acoustic and waveform modeling for singing voice synthesis based on deep neural networks

    Yukiya Hono

    Doctor Thesis, Nagoya Institute of Technology, February, 2022.

  • Development of a singing voice synthesis system based on deep neural networks

    Yukiya Hono

    Master Thesis, Nagoya Institute of Technology, February, 2019.

  • Singing voice synthesis based on deep neural networks using generative model structures

    Yukiya Hono

    Graduation Thesis, Nagoya Institute of Technology, February, 2017.

Preprint

  • Towards human-like spoken dialogue generation between AI agents from written dialogue

    Kentaro Mitsui, Yukiya Hono, and Kei Sawada

    arXiv preprint arXiv:2310.01088, October, 2023. (arXiv)

  • Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation

    Miku Nishihara, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    arXiv preprint arXiv:2301.02262, January, 2023. (arXiv)

Contact

The 5th floor of Building No.4, Tokuda, Nankaku and Hashimoto Laboratory
Nagoya Institute of Technology, Gokiso-Cho, Showa-Ku, Nagoya, 466-8555 Japan

E-mail : hono [at] nitech.ac.jp