Masaya Kawamura

LY Corporation

I am a software enginner / researcher at LY Corporation. My research interests include speech synthesis, voice conversion, music information processing, and machine learning.

Interests

• Speech Synthesis
• Voice Conversion
• Music Information Processing
• Audio Signal Processing

Education

• Master’s course in Information Science and Technology

  Graduate School of Information Science and Technology, The University of Tokyo, Japan.

• Bachelor’s degree in Science and Engineering

  Faculty of Science and Engineering, Doshisha University, Japan.

Experience

1. Software Engineer & Researcher

   LY Corporation October 2023 – Present
   Speech processing

2. Software Engineer & Researcher

   LINE Corporation April 2023 – September 2023
   Speech processing

3. Researcher

   LINE Corporation April 2022 – October 2022
   Research on text-to-speech synthesis (internship)

4. Researcher

   Yamaha Corporation August 2021 – August 2021
   Research new DNN-based model (internship)

Education

1. Master’s course in Information Science and Technology

   Graduate School of Information Science and Technology, The University of Tokyo, Japan. April 2021 – March 2023

2. Bachelor’s degree in Science and Engineering

   Faculty of Science and Engineering, Doshisha University, Japan. April 2017 – March 2021

Publications

Ryuichi Yamamoto, Yuma Shirahata, Masaya Kawamura, Kentaro Tachibana (2024). Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control. Submitted to ICASSP2025.

PDF arXiv Demo

Masaya Kawamura, Ryuichi Yamamoto, Yuma Shirahata, Takuya Hasumi, Kentaro Tachibana (2024). LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning. In Proc. Interspeech 2024.

PDF Code arXiv Demo

Reo Shimizu, Ryuichi Yamamoto, Masaya Kawamura, Yuma Shirahata, Hironori Doi, Tatsuya Komatsu, Kentaro Tachibana (2023). PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions. In Proc. ICASSP2024.

PDF arXiv Demo Code HuggingFace Demo

Masaya Kawamura, Yuma Shirahata, Ryuichi Yamamoto, Kentaro Tachibana (2023). Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform. In Proc. ICASSP2023.

PDF Code arXiv Demo

川村 真也, 中村 友彦, 高宗 典玄, 北村 大地, 猿渡 洋, 高橋 祐, 近藤 多伸 (2022). 混合Differentiable Digital Signal Processingモデルによる合成パラメータ抽出のためのラウドネスの時間変動に基づくロス関数の設計. 日本音響学会 2022年秋季研究発表会.

See all publications

Award & Grants

IEEE Signal Processing Society Japan Student Conference Paper Award

Dec 1, 2022

Google Travel and Conference Grants

Mar 1, 2022

Talks

ICASSP2023音声・音響読み会

タイトル：Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform

Jul 7, 2023

ICASSP2022音声読み会

タイトル：#10 Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds

Jun 10, 2022