Chung-Ming Chien (簡仲明)

Chicago, Illinois, United States


Jiaming Lake, Taiwan

July 31, 2022

I am a Ph.D. student at Toyota Technological Institute at Chicago (TTIC), working with Karen Livescu. My research interests cover speech and NLP. Recently, I am particularly interested in the development, analysis, and application of self-supervised representations.

Before joining TTIC, I received my Master’s degree in Computer Science at National Taiwan University (NTU) under the supervision of Lin-shan Lee and Hung-yi Lee in the Speech Processing Lab. I also joined the TTS Research Group of Amazon Alexa in Cambridge, UK, as a science intern in the autumn of 2021.

Aside from being a researcher, I am a sports enthusiasts and an amateur athlete. I captained the baseball varsity team of NTU during my undergraduate years, and I am also broadly interested in tennis, hiking, scuba diving, marathon, swimming, badminton, and training!


Feb 2, 2023 I’ll join Meta Fundamental AI (FAIR) Labs in 2023 summer. Excited about working on large-scale projects of speech and language modeling
Dec 15, 2022 My open-source FastSpeech 2 project gets over 1000 stars on Github :sparkles:
Nov 18, 2022 I gave a talk at the TTIC Student Workshop with the topic of Self‐Supervised Pre‐Trained Voice Conversion!
Sep 27, 2022 I joined the Speech and Language Group at TTIC as a Ph.D. student. New life in Chicago!
Jan 22, 2022 Voice Filter was accepted by ICASSP 2022. Thanks my team members from Amazon during my wonderful internship in Cambridge :gb:
Jun 30, 2021 I finished my thesis defense and received my Master’s degree from NTU. Thanks my thesis committee and my advisors, Lin-shan Lee and Hung-yi Lee! :mortar_board:

selected publications

  1. Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech
    Chung-Ming Chien, Jheng-Hao Lin, Chien-yu Huang, and 2 more authors
    In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Jun 2021
  2. FragmentVC: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention
    Chung-Ming Chien*, Yist Y. Lin*, Jheng-Hao Lin, and 2 more authors
    *equal contribution
    In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Jun 2021
  3. Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis
    Chung-Ming Chien, and Hung-yi Lee
    In 2021 IEEE Spoken Language Technology Workshop (SLT) Jan 2021