Table of Content
- About Me
- Work Experience
- Extracurricular Experience
- Honors
- Presentations
- Publications
- Professional Volunteer Experience
- Teaching Assistant Experience
- Interests
About Me
My name is Andy T. (Ting-Wei) Liu. I received my Ph.D. degree in the College of Electrical Engineering & Computer Science (EECS) from the National Taiwan University (NTU), Taipei, Taiwan, in 2024, supervised by Professor Hung-Yi Lee. I’m from the “Speech Processing and Machine Learning” laboratory at NTU, also working with Professor Lin-shan Lee.
I offer more than five years of dedicated experience in machine learning, self-supervised learning, foundation models, and generative models for speech and NLP.
My scholarly impact is affirmed by over 1,500 citations and an h-index of 12 on Google Scholar. The IEEE Signal Processing Society has identified one of my publications, “TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech”, as one of the top 25 downloaded articles from Sept. 2021 - Sept. 2022 for IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) on IEEE Xplore®.
My colleague Shu-wen (Leo) Yang and I founded the S3PRL Toolkit in 2019 – now celebrated with over 2,000 stars on GitHub – and have kept developing ever since. Our S3PRL Toolkit provides an easy-to-use interface to the research community, including self-supervised foundation models and downstream tasks.
Work Experience
- Applied Scientist Intern
AWS (Amazon Web Services)
New York, U.S.A, Jun. 2021 - Oct. 2021.- Worked with the Amazon Transcribe team under the supervision of Andrew Arnold and Wei Xiao.
- Completed a research paper that uses prompting foundation models to achieve low-resource NER (Named Entity Recognition).
- Built fully automated machine learning NLP pipelines for few-shot NLP using PyTorch and Huggingface.
- Implemented several few-shot baselines and adopted them on multiple datasets.
- Worked with the Amazon Transcribe team under the supervision of Andrew Arnold and Wei Xiao.
- Ph.D. Student Program
AICS (ASUS Intelligent Cloud Services)
Taipei, Taiwan, Nov. 2021 - Jun. 2023.- Worked with the AICS Singapore AI research team under the supervision of Stefan Winkler.
- Worked on research projects developing AI solutions in the healthcare sector.
- Worked with the AICS Singapore AI research team under the supervision of Stefan Winkler.
- Ph.D. Student Program
AICS (ASUS Intelligent Cloud Services)
Taipei, Taiwan, Sep. 2020 - Jun. 2021.- Worked with the AICS medical team under the supervision of Professor Chih-Jen Lin and Professor Victor Tsai.
- Worked on representation learning algorithms that encode patient information in the medical domain.
- Worked with the AICS medical team under the supervision of Professor Chih-Jen Lin and Professor Victor Tsai.
Extracurricular Experience
- The S3PRL Toolkit: Self-Supervised Speech Pre-training and Representation Learning [ repo ]
- SUPERB: Speech processing Universal PERformance Benchmark [ website ]
- ZeroSpeech TTS-without-T Challenge [ repo ]
- Tacotron English TTS [ repo ]
- Tacotron Code-Switch TTS [ repo ]
- Sequence GAN Chatbot [ repo ]
Honors
ASUS Ph.D. Scholarship (華碩AI研發中心博士生學位計畫) Sep. 2020 - Jun. 2023
Merry Electro-Acoustic Thesis Award - 1st Place (美律電聲論文獎 - 金質獎) 2020
NTU Frontier Speech Technology Scholarship (國立臺灣大學前瞻語音科技獎學金) Oct. 2019 - Aug. 2020
FAOS Outstanding Students Conference Travel Grant (傑出人才優秀學生出國開會補助) 2019
NTU Electrical Engineering Innovation Award - 2nd place (國立臺灣大學電機系精專獎 - 貳獎) 2017
Macau Government Lotus Award (澳門政府蓮花獎) 2014
Presentations
- Lecture in MLSS 2021 TAIPEI (Machine Learning Summer School), presenter of The S3PRL Toolkit Tutorial: Self-Supervised Speech Pre-training and Representation Learning, Taipei, Taiwan, Aug 2021
- Lecture in Department of Electrical Engineering at NTU, presenter of the lecture Audio BERT in the Deep Learning for Human Language Processing course, Taipei, Taiwan, June 2020
- Talk at ASUSTeK Computer Inc., presenter of the talk Self-Supervised Learning for Speech, Taipei, Taiwan, May 2020
- ICASSP 2020 Lecture Session, presenter of the paper Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders, Virtual, Online, May 2020
- Talk at National Taiwan University, presenter of the paper Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders, NTU, Taipei, Taiwan, February 2020
- INTERSPEECH 2019 Oral Session, presenter of the paper Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion, Graz, Austria, September 2019
Publications
*Sorted by recency
Parallel Synthesis for Autoregressive Speech Generation
Po-chun Hsu, Da-rong Liu, Andy T. Liu, Hung-yi Lee
Published in IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 31, 2023 (TASLP)
[ ieee | arxiv ]QaNER: Prompting question answering models for few-shot named entity recognition
Andy T. Liu, Wei Xiao, Henghui Zhu, Dejiao Zhang, Shang-Wen Li, Andrew Arnold
Work done while interning at Amazon AI. arXiv preprint, 2022, Cornell University
[ arxiv | pdf ]SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-wen Yang, Shuyan Dong, Andy T. Liu, Cheng-I Jeff Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
Accepted by ACL 2022, conference organized by the Association for Computational Linguistics Association (ISCA)
[ acl | arxiv | pdf | code ]SUPERB: Speech processing Universal PERformance Benchmark
Shu-wen Yang, Andy T Liu, Po-Han Chi, Yung-Sung Chuang, Cheng-I Jeff Lai, Kushal Lakhotia, Yist Y Lin, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
Accepted by INTERSPEECH 2021, conference organized by the International Speech Communication Association (ISCA)
[ isca | arxiv | pdf | code ]Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning
Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee
Published in IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 30, 2021 (TASLP)
[ ieee | arxiv | pdf | code ]Don’t Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models
Yen Meng, Yi-Hui Chou, Andy T. Liu, Hung-yi Lee
Lecture session in ICASSP 2022, conference organized by the IEEE Signal Processing Society (SPS)
[ ieee | arxiv | pdf | code ]TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
Andy T. Liu, Shang-Wen Li, Hung-yi Lee
Published in IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 29, 2021 (TASLP)
[ ieee | arxiv | pdf | code ]Adversarial Defense for Automatic Speaker Verification by Cascaded Self-Supervised Learning Models
Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee
Virtual session in ICASSP 2021, a conference organized by the IEEE Signal Processing Society (SPS)
[ ieee | arxiv | pdf | code ]Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning
Haibin Wu, Andy T. Liu, Hung-yi Lee
Virtual session in INTERSPEECH 2020, a conference organized by the International Speech Communication Association (ISCA)
[ isca | arxiv | pdf | code ]Understanding Self-Attention of Self-Supervised Audio Transformers
Shu-wen Yang, Andy T. Liu, Hung-yi Lee
Virtual session in INTERSPEECH 2020, a conference organized by the International Speech Communication Association (ISCA)
[ isca | arxiv | pdf | demo ]Towards Robust Neural Vocoding for Speech Generation: A Survey
Po-chun Hsu, Chun-hsuan Wang, Andy T. Liu, Hung-yi Lee
arXiv preprint, 2020, Cornell University
[ arxiv | pdf | demo ]Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, Hung-yi Lee
Lecture session in ICASSP 2020, a conference organized by the IEEE Signal Processing Society (SPS)
[ ieee | arxiv | pdf | code | slide | talk ]Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
Andy T. Liu, Po-chun Hsu, Hung-yi Lee
Oral session in INTERSPEECH 2019, conference organized by the International Speech Communication Association (ISCA)
[ isca | arxiv | pdf | code | slide ]
Professional Volunteer Experience
Official reviewer of IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) Journal, 2024
Official reviewer of ICASSP 2024 Conference, 2024
Official reviewer of ICASSP 2023 Conference, 2023
Official reviewer of IEEE Open Journal of Signal Processing (OJSP) Journal, 2023
Official reviewer of IEEE Open Journal of Signal Processing (OJSP) Journal, 2022
Official reviewer of IEEE Journal of Selected Topics in Signal Processing (JSTSP) Journal, 2022
Official reviewer of ICASSP 2022 Conference, 2022
Official reviewer of ISCSLP 2022 Conference, 2022
Official reviewer of EMNLP 2021 Conference, 2021
Official reviewer of NeurIPS Workshop: Self-Supervised Learning for Speech and Audio Processing Workshop, 2020
Review Helper of IEEE/ACM TASLP Journal, 2020
Review Helper of ISCSLP 2020 Conference, 2020
Review Helper of AAAI 2020 Conference, 2020
Review Helper of AAAI 2019 Conference, 2019
Review Helper of ICASSP 2020 Conference, 2019
Review Helper of INTERSPEECH 2019 Conference, 2019
Review Helper of ACMSE 2019 Conference, 2019
Teaching Assistant Experience
TA of Machine Learning Special Project NTU EECS, 2018-Pres.
TA of Machine Learning and Having it Deep and Structured NTU EECS, Fall 2019
Interests
- PADI Scuba Diving Instructor, May. 2023 - Present
- Scuba Diving, Jul. 2020 - Present
- Photographer, Amateur, Nov. 2021 - Present
- Guitar, Amateur, Oct. 2016 - Jan. 2020
- Road Biking, (NTU Cycling Club), Jun. 2014 - Aug. 2017
- Pet geckos: Instagram
Contact
Write me if you are looking for a collaboration!