About Me

I recently finished my Master's study in Computer Science at National Taiwan University (NTU) in August, 2021. During my graduate years, I was a member of the Speech Processing Laboratory led by Prof. Lin-shan Lee and Prof. Hung-yi Lee. I also joined the TTS Research Group of Amazon Alexa in Cambridge, UK, as a science intern in the autumn of 2021.

My research interests include deep learning and its applications in speech processing and natural language processing. Recently I focus on the following topics.

  • applications of self-supervised speech representations
  • low-resource speech processing and voice construction
  • speaker representation learning

Education

National Taiwan University (NTU)

M.S., Computer Science and Information Engineering

Sep. 2019 - Aug. 2021
  • Advised by Prof. Lin-shan Lee and Prof. Hung-yi Lee
  • Speech Processing Laboratory
  • GPA: 4.02/4.3

National Taiwan University (NTU)

B.S.E, Electrical Engineering

Sep. 2015 - Aug. 2019
  • GPA: 4.08/4.3
  • Rank: 25-th out of 256 students

Experience

Laboratories

NTU Speech Processing Lab.

Sep. 2018 - July 2021
  • Disentangled speaker and phonetic information in speech with self-supervised features
  • Speaker representation obtained from generative and self-supervised pre-training
  • Low-resource voice construction
  • Prosody modeling in text-to-speech (TTS)

Machine Learning and Estimation Theory Lab.

Feb. 2017 - Feb. 2018

Hacked and fixed privacy-preserving machine learning algorithms

Internship

Amazon Alexa, Cambridge, UK

July 2021 - Nov. 2021
  • Developed extremely low-resource speaker adaptation in the Alexa TTS Research Group

Talks

Deep Learning for Speech Synthesis, at AI Summer School 2020

Aug. 2020

Optimization for Deep Learning, at NTU EECS

Apr. 2020

Teaching Assistants

Machine Learning, NTU GICE

2020 Spring

Speech Processing Project, NTU CSIE

2019 Autumn - 2020 Spring

Digital Speech Processing, NTU CSIE

2019 Autumn

Machine Learning, NTU GICE

2019 Spring

Signals and Systems, NTU EE

2018 Spring

Honors

Scholarship

NTU Advanced Speech Technologies Scholarship

Sep. 2020

NTUEE60 Scholarship

Sep. 2016

Awards

2nd Place, IEEE ICASSP 2021 M2VoC Challenge

Grand challenge of ICASSP 2021 with more than 150 teams registered

Feb. 2021

Dean's List Awards at NTU (Two-Time)

Jun. 2016 / Jun. 2017

Top 20, Trans Action Award

Trans Action Award is an innovative competition combining software engineering, UI/UX, marketing, and design, etc

May 2020

Extracurricular

Captain of NTU Baseball Varsity

May 2019 - Jun. 2020

5-th Place (Two-Time), University Baseball League of Taiwan

Mar. 2019 / Mar. 2021

Golden Medal, Men’s Half-Iron Relay, Yilan National Triathlon Championships

Sep. 2019

Publications

  1. Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis
    Chung-Ming Chien and Hung-yi Lee
    2021 IEEE Spoken Language Technology Workshop (SLT)
    Paper Demo
  2. FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments with Attention
    Chung-Ming Chien (co-first), Yist Y. Lin (co-first), Jheng-Hao Lin, Hung-yi Lee, and Lin-shan Lee.
    ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
    Paper Demo Code
  3. 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, Po-chun Hsu, and Hung-yi Lee.
    ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
    Paper Demo Code
  4. S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations
    Jheng-hao Lin, Yist Y. Lin, Chung-Ming Chien and Hung-yi Lee.
    InterSpeech 2021.
    Paper Demo Code

Projects

  1. FastSpeech 2 GitHub stars GitHub forks
    Jun. 2020

    First publicly available implementation of FastSpeech 2, which supports multiple languages and more than 100 speakers