publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. OJSP
    Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
    Ryota Komatsu, Kota Kawakita, Takuma Okamoto, and 1 more author
    IEEE Open Journal of Signal Processing, 2026
  2. A Systematic Overview of Speech Language Models
    Ryota Komatsu
    THE JOURNAL OF THE ACOUSTICAL SOCIETY OF JAPAN, 2026
  3. Invited Talk
    Syllable-Text Interleavingに基づく音声言語モデルの効率的スケーリング
    Ryota Komatsu
    日本音響学会九州支部第3回オンラインセミナー, Feb 2026

2025

  1. Invited Talk
    A Comprehensive Overview of Audio Language Models
    Ryota Komatsu
    Sixth Joint Meeting Acoustical Society of America and Acoustical Society of Japan, Oct 2025
  2. Invited Talk
    マルチモーダル大規模言語モデル入門
    Ryota Komatsu
    OTOGAKU Symposium, Jun 2025

2024

  1. SLT
    Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT
    Ryota Komatsu and Takahiro Shinozaki
    In Proc. IEEE Spoken Language Technology Workshop, Dec 2024

2023

  1. ICASSP
    Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder
    Ryota Komatsu, Yusuke Kimura, Takuma Okamoto, and 1 more author
    In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, 2023
  2. Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding
    Ryota Komatsu, Yusuke Kimura, Takuma Okamoto, and 1 more author
    In Proc. The 2023 Spring meeting of the Acoustical Society of Japan, 2023

2022

  1. JSTSP
    Automatic Spoken Language Acquisition Based on Observation and Dialogue
    Ryota Komatsu, Shengzhou Gao, Wenxin Hou, and 9 more authors
    IEEE Journal of Selected Topics in Signal Processing, 2022

2021

  1. EUSIPCO
    A Graph Regularized RPCA by Generalized Moreau Enhanced Model
    Ryota Komatsu, Masao Yamagishi, and Isao Yamada
    In Proc. 29th European Signal Processing Conference, 2021