first_name@google.com
New York, NY
Hi! Welcome to Muqiao Yang's homepage. I am a research scientist at Google Speech Team. Previously, I obtained my PhD degree from Carnegie Mellon University and bachelor degree from The Hong Kong Polytechnic University. My research interest is mainly in speech processing & natural language processing!
I enjoy talking to and learn from different people, especially helping junior PhD/Masters/Undergrad students about research, career plans, and life. Feel free to drop an email if you would like to talk!
Education
-
Ph.D. in Electrical and Computer Engineering, Carnegie Mellon University May 2024
Advisor: Prof. Bhiksha Raj, Prof. Shinji Watanabe
-
M.S. in Electrical and Computer Engineering, Carnegie Mellon University Dec 2019
-
B.E. in Electronic and Information Engineering, The Hong Kong Polytechnic UniversityMay 2018
Advisor: Prof. Man Wai Mak
-
Minor in Computer Science, The Hong Kong Polytechnic UniversityAug 2015 - May 2018
Experience
-
Research Scientist, GoogleMay 2024 - present
-
Research Intern, Google & DeepmindSept 2023 - Dec 2023
-
Research Intern, Tencent AI LabMay 2023 - Aug 2023
Mentor: Dr. Chunlei Zhang, Yong Xu
-
Research Intern, Microsoft ResearchMay 2022 - Aug 2022
Mentor: Dr. Xiaofei Wang, Naoyuki Kanda
-
Graduate Research Assistant, Carnegie Mellon UniversityDec 2021 - May 2024
Advisor: Prof. Shinji Watanabe, Bhiksha Raj
-
Graduate Research Assistant, Carnegie Mellon UniversitySept 2020 - Dec 2021
Advisor: Prof. Ian Lane
-
Research Associate, Carnegie Mellon UniversityDec 2019 - Sept 2020
Advisor: Prof. Ruslan Salakhutdinov
-
Graduate Research Assistant, Carnegie Mellon UniversityNov 2018 - Dec 2019
Advisor: Prof. Ruslan Salakhutdinov, Louis-Philippe Morency
-
Research Intern, State Key Lab of Computer Arcitechture, Institue of Computing Technology, Chinese
Academy of SciencesMay 2018 - Jul 2018Advisor: Prof. Shimin Chen
Publications
uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models
Muqiao Yang, Chunlei Zhang, Yong Xu, Zhongweiyang Xu, Heming Wang, Bhiksha Raj, Dong Yu
Rethinking Voice-Face Correlation: A Geometry View
Xiang Li, Yandong Wen, Muqiao Yang, Jinglu Wang, Rita Singh, Bhiksha Raj
ACM Multimidea (MM), 2023
[pdf]
Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions
Heming Wang, Meng Yu, Hao Zhang, Chunlei Zhang, Zhongweiyang Xu, Muqiao Yang, Yixuan Zhang, Dong Yu
preprint
[pdf]
SpatialCodec: Neural Spatial Speech Coding
Zhongweiyang Xu, Yong Xu, Vinay Kothapally, Heming Wang, Muqiao Yang, Dong Yu
preprint
[pdf]
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Umberto Cappellazzo, Muqiao Yang, Falavigna Daniele, Alessio Brutti.
Conference of the International Speech Communication Association (InterSpeech), 2023
[pdf]
Backdoor Attacks with Input-unique Triggers in NLP
Xukun Zhou, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, Muqiao Yang, Jun He
preprint
[pdf]
Simulating realistic speech overlaps improves multi-talker ASR
Muqiao Yang, Naoyuki Kanda, Xiaofei Wang, Jian Wu, Sunit Sivasankaran, Zhuo Chen, Jinyu Li, Takuya Yoshioka
International Conference on Acoustics, Speech and Signal (ICASSP), 2023
[pdf]
PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement
Muqiao Yang, Joseph Konan, David Bick, Yunyang Zeng, Shuo Han, Anurag Kumar, Shinji Watanabe, Bhiksha Raj
International Conference on Acoustics, Speech and Signal (ICASSP), 2023
TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement
Yunyang Zeng, Joseph Konan, Shuo Han, David Bick, Muqiao Yang, Anurag Kumar, Shinji Watanabe, Bhiksha Raj
International Conference on Acoustics, Speech and Signal (ICASSP), 2023
Improving Speech Enhancement through Fine-Grained Speech Characteristics
Muqiao Yang*, Joseph Konan*, David Bick*, Anurag Kumar, Shinji Watanabe, Bhiksha Raj
Conference of the International Speech Communication Association (InterSpeech), 2022
Online Continual Learning of End-to-End Speech Recognition Models
Muqiao Yang, Ian Lane, Shinji Watanabe
Conference of the International Speech Communication Association (InterSpeech), 2022
[pdf]
Self-supervised Representation Learning with Relative Predictive Coding
Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Ruslan Salakhutdinov, Louis-Philippe Morency
International Conference on Learning Representations (ICLR), 2021
Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis
Yao-Hung Hubert Tsai*, Martin Q. Ma*, Muqiao Yang*, Ruslan Salakhutdinov, Louis-Philippe Morency
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
Complex Transformer: A Framework for Modeling Complex-Valued Sequence
Muqiao Yang*, Martin Q. Ma*, Dongyu Li, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov
International Conference on Acoustics, Speech and Signal (ICASSP), 2020
Neural Information Processing Systems (NeurIPS) Science meets Engineering of Deep Learning workshop, 2019 (Oral)
Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
Qiqi Xiao, Jiaxu Zou, Muqiao Yang, Alex D. Gaudio, Kris Kitani, Asim Smailagic, Pedro Costa, Min Xu
International Conference on Image Analysis and Recognition, 2019
Storing and Querying Large-Scale Spatio-Temporal Graphs with High-Throughput Edge Insertions
Mengsu Ding, Muqiao Yang, Shimin Chen
arXiv preprint arXiv:1904.09610, 2019
[pdf]
Teaching
- 11-785, Introduction to Deep Learning, Spring 2023, Fall 2023, Spring 2024
- 18-661, Introduction to Machine Learning for Engineers, Fall 2022
- 18-660, Optimization, Spring 2022
- 10-605, Machine Learning with Large Datasets, Fall 2021
Service
- Reviewer at NeurIPS, EMNLP, ICASSP, Interspeech, SLT, AACL-IJCNLP, Speech Communication