Jianing Yang

Master's student at Saruwatari & Saito lab, The University of Tokyo.

yjn.jpg

Room #141, Engineering bldg. #6, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

I am Jianing Yang, a Master’s student in Creative Informatics at the University of Tokyo, advised by Prof. Hiroshi Saruwatari. My research interests lie in speech processing and generative models, including expressive TTS, speech-to-speech, and end-to-end dialog systems. Previously, I worked as an AI/Research Engineer Intern at Huawei Japan, IVRy Inc., SB Intuitions, and NTT Human Informatics Laboratories, focusing on efficient vision models and advanced speech generation.

Before UTokyo, I received my B.Eng. in Information and Communications Engineering at Institute of Science Tokyo (advised by Prof. Takahiro Shinozaki). I enjoy building practical systems that blend state-of-the-art models with reliable engineering.

Feel free to reach me via email, and check my publications and cv pages for more details.

selected publications

  1. APSIPA TTS
    Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement
    Jianing Yang , Sheng Li , Takahiro Shinozaki , Yuki Saito and Hiroshi Saruwatari
    In Proceedings of the 17th Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2025) , Oct 2025
  2. ICASSP Speech Evaluation
    DistilMOS: Layer-wise Self-distillation for Self-Supervised Learning Model-based MOS Prediction
    Jianing Yang , Wataru Nakata , Yuki Saito and Hiroshi Saruwatari
    In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026) , May 2026
  3. ICASSP Speech Corpus
    SS-JDSC: Single-Speaker Japanese Dysarthric Speech Corpus
    Asahi Ogasawara* , Shinnosuke Takamichi* , Jianing Yang* , Go Suenaga and Yiyu Tan (* equal contribution)
    In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026) , May 2026