Scholar
Jiatong Shi (史嘉彤)
Google Scholar ID: FEDNbgkAAAAJ
Carnegie Mellon University
Speech Processing
Speech Recognition
Music Processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
4,112
H-index
29
i10-index
55
Publications
20
Co-authors
196
list available
Contact
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Resume
Academic Achievements
Authored over 70 publications in leading speech and machine learning conferences
Best Paper Award at ISCA Interspeech 2024
Best Paper Award at EMNLP 2024
Recipient of the CMU Presidential Fellowship
First author of NAACL 2025 demo paper: 'VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music'
Co-author of ICASSP 2025 paper: 'Preference Alignment Improves Language Model-Based TTS'
Finalist in the AI Song Contest 2022 with submission 'Be With You'
Research Experience
Conducting research on speech representation learning and applications under the supervision of Prof. Shinji Watanabe
Leading a joint team on music processing, including automatic songwriting, music transcription, and singing voice synthesis
Currently focusing on singing voice synthesis, advised by Prof. Qin Jin
Actively contributing to the ESPnet project (Muskits merged into ESPnet)
Served as a teaching assistant for CMU’s NLP course (11-411/611) in 2022 and delivered a lecture on speech processing
Co-hosted an ESPnet tutorial at JSALT 2022 summer school with Leo Yang
Co-authors
17 total
Shinji Watanabe
Carnegie Mellon University
Xuankai Chang
Apple AI/ML
Hung-yi Lee
National Taiwan University
Jinchuan Tian
Language Technologies Institute, Carnegie Mellon University
William Chen
Carnegie Mellon University
Yifan Peng
NVIDIA
Abdelrahman Mohamed
Research scientist, Facebook AI Research
Qin Jin
中国人民大学信息学院