About me

I am a PhD student at Carnegie Mellon University’s Language Technologies Institute, advised by Professor Shinji Watanabe, as a part of the Audio and Voice Lab. My work at CMU has focused on building large-scale speech foundation models. I am interested in methods that can make speech models more generally useful and rely less on human supervision/effort or modelling assumptions. This includes topics like self-supervised speech representation learning, multilingual speech processing, and long-form speech processing.

Previously, I was a Software Engineer at Texas Instruments, as part of the Ti.com e-commerce team. This collection of articles details some of the work I did on the team.

I received my Master’s in Language Technologies from CMU LTI in May 2024, and my BS in Computer Science and BA in History from the University of Central Florida in May 2021.

Selected Publications

Google Scholar will be more up-to-date.

Towards Robust Speech Representation Learning for Thousands of Languages
_{William Chen, Wangyou Zhang, Yifan Peng, Xinjian Li, Jinchuan Tian, Jiatong Shi, Xuankai Chang, Soumi Maiti, Karen Livescu, Shinji Watanabe}
_{EMNLP 2024, Best Paper Award}
_paper

EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios
_{Tejes Srivastava, Jiatong Shi, William Chen, Shinji Watanabe}
_{INTERSPEECH 2024, Best Paper Award}
_paper

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
_{Yifan Peng, Jinchuan Tian, William Chen, Siddhant Arora, Brian Yan, Yui Sudo, Muhammad Shakeel, Kwanghee Choi, Jiatong Shi, Xuankai Chang, Jee-weon Jung, Shinji Watanabe}
_{INTERSPEECH 2024}
_paper

Train Long and Test Long: Leveraging Full Document Contexts in Speech Processing
_{William Chen, Takatomo Kano, Atsunori Ogawa, Marc Delcroix, Shinji Watanabe}
_{ICASSP 2024} _paper

Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
_{Yifan Peng, Jinchuan Tian, Brian Yan, Dan Berrebbi, Xuankai Chang, Xinjian Li, Jiatong Shi, Siddhant Arora, William Chen, Roshan Sharma, Wangyou Zhang, Yui Sudo, Muhammad Shakeel, Jee-weon Jung, Soumi Maiti, Shinji Watanabe}
_{ASRU 2023}
_paper

Joint Prediction and Denoising for Large-Scale Multilingual Self-Supervised Learning
_{William Chen, Jiatong Shi, Brian Yan, Dan Berrebbi, Wangyou Zhang, Yifan Peng, Xuankai Chang, Soumi Maiti, Shinji Watanabe}
_{ASRU 2023}
_paper

Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute
_{William Chen, Xuankai Chang, Yifan Peng, Zhaoheng Ni, Soumi Maiti, Shinji Watanabe}
_{INTERSPEECH 2023}
_paper

Improving Massively Multilingual ASR With Auxiliary CTC Objectives
_{William Chen, Brian Yan, Jiatong Shi, Yifan Peng, Soumi Maiti, Shinji Watanabe}
_{ICASSP 2023, Top 3% Paper Award, SPS Student Travel Grand Award}
_paper

Past Positions

From May 2023 to August 2023, I was a Research Intern at the NTT Communication Sciences Lab in Japan, supervised by Marc Delcroix, Atsunori Ogawa, and Takatomo Kano.

From April 2021 to July 2021, I was part of the UCF Security and Analytics Lab, supervised by Professor David Mohaisen.

From June 2020 to July 2022, I was a Research Assistant at the UCF Computational Biology Lab, supervised by Professor Wei Zhang.

From January 2020 to October 2021, I was part of the UCF Evolutionary Computation Lab, supervised by Professor Annie Wu.

William Chen

Recent News

Selected Publications

Past Positions