Ja | En

PUBLICATIONS

Peer-Reviewed International Conferences

Phonological Tokenizer: Prosody-Aware Phonetic Token via Multi-Objective Fine-Tuning with Differentiable K-Means
Kentaro Onda, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
ICASSP2026 (Accepted) [arXiv]
Advanced Modeling of Interlanguage Speech Intelligibility Benefit with L1-L2 Multi-Task Learning Using Differentiable K-Means for Accent-Robust Discrete Token-Based ASR
Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
ICASSP2026 (Accepted) [arXiv]
Benchmarking Prosody Encoding in Discrete Speech Tokens
Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
ASRU2025 [arXiv]
Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data
Kentaro Onda, Keisuke Imoto, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
Interspeech2025 [ISCA Archive] [arXiv]
Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corpora
Kentaro Onda, Keisuke Imoto, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
Interspeech2025 [ISCA Archive] [arXiv]
Differentiable K-means for Fully-optimized Discrete Token-based ASR
Kentaro Onda, Yosuke Kashiwagi, Emiru Tsunoo, Hayato Futami, Shinji Watanabe
Interspeech2025 [ISCA Archive] [arXiv]
A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora
Kentaro Onda, Joonyong Park, Nobuaki Minematsu, Daisuke Saito
Interspeech2024 [ISCA Archive] [arXiv]

Non-peer-reviewed Domestic Conferences

Probabilistic Use of Discrete Speech Tokens Derived from SSL Models for Downstream Task Inference
Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
Proc. 2026 Spring Meeting of the Acoustical Society of Japan
Advanced Simulation of Interlanguage Speech Intelligibility Benefit via Multi-task Learning of L1/L2 Using Differentiable K-means for Accent-robust ASR
Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
IPSJ SIG Technical Report, SLP-158, 2025 (Encouragement Award)
An Analytical Study on the Prosodic Encoding of Discrete Speech Tokens
Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
Proc. 2025 Autumn Meeting of the Acoustical Society of Japan
Exploring the usage of discrete tokens for accent-robust automatic speech recognition only using native speech corpora
Kentaro Onda, Satoru Fukayama, Keisuke Imoto, Daisuke Saito, Nobuaki Minematsu
Proc. 2025 Spring Meeting of the Acoustical Society of Japan (Best Student Presentation Award)
Modeling and Predicting Individual Learners' Performance of Prosody Imitation and its Use for Material Selection
Xiai Cheng, Haipeng Geng, Kentaro Onda, Daisuke Saito, Nobuaki Minematsu
Proc. 2025 Spring Meeting of the Acoustical Society of Japan
Improved Foreign Accent Simulation Using Only Native Speech Corpora Based on Discrete Token Duration Prediction
Kentaro Onda, Joonyong Park, Keisuke Imoto, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
IPSJ SIG Technical Report, SLP-154, 2024
Analyzing Language Learners' Oral Imitation Through Machine Model of Oral Imitation with Foreign Accentuation
Xiai Cheng, Kentaro Onda, Daisuke Saito, Nobuaki Minematsu
Proc. 2024 Autumn Meeting of the Acoustical Society of Japan
Synthesis of Foreign Accented Speech by Self-supervised Learning Only Using Native Speech Corpora
Kentaro Onda, Joonyong Park, Daisuke Saito, Nobuaki Minematsu
IPSJ SIG Technical Report, SLP-152, 2024 (Best Presentation Award)
Generating foreign accented speech using native speech corpus only for training
Kentaro Onda, Joonyong Park, Nobuaki Minematsu, Daisuke Saito
Proc. 2024 Spring Meeting of the Acoustical Society of Japan

Abstract-reviewed Conferences (no proceedings)

Simulation of Foreign Accentuation by Discrete Symbol-based Resynthesis Using Only Native Speech Corpora
Kentaro Onda, Joonyong Park, Daisuke Saito, Nobuaki Minematsu
Eighth International Workshop on Symbolic-Neural Learning (SNL2024)

COMPETITIVE FUNDS

Oct. 2025 - Mar. 2028
JST ACT-X
"Development of a Speaker-invariant Speech Representation Learning Model Based on Structural Phonology", 4,500,000 JPY
Jul. 2024 - Mar. 2025
AIST KAKUSEI Project
"Accent-robust Automatic Speech Recognition Only Using Native Speech Corpora", 3,000,000 JPY

AWARDS

Dec. 2025
Encouragement Award in Spoken Language Processing and Natural Language Processing Symposium (Special Session)
Sep. 2025
Best Student Presentation Award of ASJ
Aug. 2025
Travel Grant Award for Interspeech2025, 1000 EUR
Jun. 2024
2024 Otogaku Symposium Best Presentation Award