About Me

Hello! I’m Roger, an 2nd-year masters student currently working on several topics in unsupervised speech processing at NTU Speech Processing and Machine Learning Lab supervised by Prof. Lin-shan Lee and Prof. Hung-yi Lee. I used to work on unsupervised music source separation, and I also have experience in various applied ML projects.

Publications

• REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
  Liang-Hsuan Tseng, En-Pei Hu, Cheng-Han Chiang, Yuan Tseng, Hung-yi Lee, Lin-shan Lee, Shao-Hua Sun
  in submission
  [paper] [code] (TBA)

• AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models
  Yuan Tseng, Layne Berry, Yi-Ting Chen, I-Hsiang Chiu, Hsuan-Hao Lin, Max Liu, Puyuan Peng, Yi-Jen Shih, Hung-Yu Wang, Haibin Wu, Po-Yao Huang, Chun-Mao Lai, Shang-Wen Li, David Harwath, Yu Tsao, Shinji Watanabe, Abdelrahman Mohamed, Chi-Luen Feng, Hung-yi Lee
  ICASSP 2024
  [paper] [code] [submission platform]

• Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences
  Yuan Tseng, Cheng-I Lai, Hung-yi Lee
  ICASSP 2023
  [paper] [code]

• On the Utility of Self-supervised Models for Prosody-related Tasks
  Guan-Ting Lin*, Chi-Luen Feng*, Wei-Ping Huang^, Yuan Tseng^, Tzu-Han Lin^, Chen-An Li^, Hung-yi Lee, Nigel G. Ward.
  SLT 2022 (Best Paper Award)
  [paper] [code]

Talks

• AV-SUPERB: Audio-visual Representations and How to Evaluate Them, ASRU 2023 SPARKS workshop [slides]