Ryuichi Yamamoto

Ryuichi Yamamoto

Engineer/Researcher

LINE Corporaiton

Nagoya University

About me

I am a software engineer / researcher at LINE Corporation. I am also a Ph.D. student at at Nagoya University, working with my advisor Prof. Tomoki Toda at the Toda Laboratory.

My research interests include statistical speech synthesis, voice conversion, singing voice synthesis, and machine learning. Before joining LINE Corporation, I worked in music signal processsing, music information retrieval, and computer vision.

Interests
  • Speech Synthesis
  • Voice Conversion
  • Generative Models
Education

  • Ph.D course in Informatics, April 2022 -

    Nagoya University

  • M.Eng in Compute Science, 2013

    Nagoya Institude of Technology

  • B.Eng in Computer Science, 2011

    Nagoya Institude of Technology

Projects

NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit
Accepted to ICASSP 2023
Ryuichi Yamamoto, Reo Yoneyama, Tomoki Toda
Non-parallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs
Accepted to ICASSP 2023
Reo Yoneyama, Ryuichi Yamamoto, Kentaro Tachibana
Period VITS: Variational Inference With Explicit Pitch Modeling For End-to-End Emotional Speech Synthesis
Accepted to ICASSP 2023
Yuma Shirahata, Ryuichi Yamamoto, Eunwoo Song, Ryo Terashima, Jae-Min Kim, Kentaro Tachibana
Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
Accepted to ICASSP 2023
Masaya Kawamura1, Yuma Shirahata, Ryuichi Yamamoto, Kentaro Tachibana
DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning
Accepted to Interspeech 2022
Takaaki Saeki, Kentaro Tachibana, Ryuichi Yamamoto
See all

Recent Posts

Hugo Academic を使ってウェブサイトをアップデートしました
New: https://github.com/r9y9/website, old: https://github.com/r9y9/blog
Ryuichi Yamamoto
Jan 18, 2022 1 min read
NNSVS: Pytorchベースの研究用歌声合成ライブラリ
Neural network based singing voice synthesis: https://github.com/r9y9/nnsvs
May 10, 2020 1 min read
LJSpeech は価値のあるデータセットですが、ニューラルボコーダの品質比較には向かないと思います

LJSpeech Dataset: https://keithito.com/LJ-Speech-Dataset/

Jun 11, 2019 1 min read
WN-based TTSやりました / Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions [arXiv:1712.05884]
Audio samples: https://r9y9.github.io/wavenet_vocoder/
May 20, 2018 3 min read
WaveNet vocoder をやってみましたので、その記録です / WaveNet: A Generative Model for Raw Audio [arXiv:1609.03499]
Audio samples: https://r9y9.github.io/wavenet_vocoder/
Jan 28, 2018 2 min read
See all posts

Talks

企業における音声合成の研究開発 / Research and development for TTS in industry @名古屋工業大学
Jan 25, 2022 10:30 AM — 12:00 PM
Ryuichi Yamamoto
国際会議Interspeech2021参加報告 / Report on Participation in Interspeech2021 @SLP研究会
Dec 3, 2021 1:00 PM — 2:20 PM
Tomohiro Tanaka, Ryuichi Yamamoto
ここまで来た音声技術・今後の展望 / Current progress on speech technologies and its future prospects @ LINE DEV DAY 2020
Nov 25, 2020 4:40 PM — 5:20 PM
Togami Masahito, Yusuke Kida, Ryuichi Yamamoto, Keisuke Imoto
Parallel WaveGAN: GPUを利用した高速かつ高品質な音声合成 / Parallel WaveGAN: Fast and High-Quality GPU Text-to-Speech @ LINE DEV DAY 2020
Nov 25, 2020 2:20 PM — 2:50 PM
Ryuichi Yamamoto
End-to-End 音声合成の研究を加速させるツールキット ESPnet-TTS / ESPnet-TTS: A toolkit to accelerate research on end-to-end speech synthesis @ ASJ 2020s
Mar 16, 2020 1:00 PM — 1:30 PM
Tomoki Hayashi, Ryuichi Yamamoto, Katsuki Inoue, Takenori Yoshimura, Kazuya Takemura, Tomoki Toda, Shinji Watanabe