Home

Yuchen Liu (刘雨晨)

Ph.D. Candidate

Department of Computer Science

Indiana University Bloomington

Hi, welcome to my site.

My name is Yuchen Liu and I am a fifth-year Computer Science Ph.D. candidate from Indiana University Bloomington. My advisor is Dr. Donald S. Williamson and our group info can be found here.

I have received a B.S. degree in Computer Science and a B.S degree in Financial Economics from Centre College in 2016. After that, I received a M.S. degree in Data Science from Indiana University in 2018.

Research Interest

My research interest mainly focuses on audio and speech-related deep learning tasks including audio(multimodal) representation learning, audio privacy, audio adversarial example generation, speech recognition, voice conversion, speaker verification, speech assessment and speech enhancement.

News

Mar 01 2023: Our multimodal representation learning paper "MMViT: Multiscale Multiview Vision Transformers". from Meta has been submitted to interspeech 2023!

Feb 06 2023: Our dereverberation paper "A Composite T60 Regression and Classification Approach for Speech Dereverberation". from Indiana University Bloomington has been accepted and published to IEEE Transactions on Audio, Speech and Language Processing!! [paper link]

Sep 19 2022: I will attend interspeech 2022 virtually!

Sep 9 2022: I have extended the internship for another 3 months as a student researcher to work on publications about exploring the latest large-scale audio embedding pre-training methods.

Sep 9 2022: My summer intern at the Meta is finish. It is a great experience to join the team!

Jun 20 2022: My summer intern at the Meta multimodal content understanding team has started. Excited to join the team! I will work on audio embedding part of the largest multimodal content understanding model in Meta.

Jun 15 2022: Our non-intrusive speech assessment paper "CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment " from Bose has been accepted to Interspeech 2022! [paper link]

Jun 15 2022: My paper "Preventing sensitive-word recognition using self-supervised learning to preserve user-privacy for automatic speech recognition" has been accepted to Interspeech 2022! [paper link]

March 28 2022: Our non-intrusive speech assessment paper from Bose has been submitted to ConferencingSpeech2022 challenge from Interspeech 2022 and ranked 12th!

Dec 10 2021: I will join the Bose Audio Research team next spring for a 6-month Audio ML Co-op.

Dec 1 2021: I will join the Meta AI integrity team next summer as a machine learning intern.

Jul 27 2021: Really appreciate Adam Aviv for inviting me and sharing my PETS 2021 paper in George Washington University/Usable Security and Privacy Lab (gwusec) reading group.

Jul 14 2021: I have attended the 21st Privacy Enhancing Technologies Symposium (PETS 2021) and presented our paper and poster.

Jun 06 2021: I have attended the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021).

Feb 19 2021: I have passed my qualification exam and became a Ph.D. Candidate.

Jan 30 2021: Our paper "On Loss Functions For Deep-Learning Based T60 Estimation" had been accepted by the International Conference on Acoustics, Speech, & Signal Processing (IEEE ICASSP) 2021. [paper link]

Nov 1 2020: My first paper "Defending Against Microphone-Based Attacks with Personalized Noise" had been accepted by the journal Proceedings on Privacy Enhancing Technologies (PoPETs) 2021. [paper link]

Publications

• Yuchen Liu, Natasha Ong, Kaiyan Peng, Bo Xiong, Qifan Wang, Rui Hou, Madian Khabsa, Kaiyue Yang, David Liu, Donald S. Williamson, Hanchao Yu."MMViT: Multiscale Multiview Vision Transformers." submitted to Interspeech 2023.

• Yuying Li, Yuchen Liu, and Donald S. Williamson. "A Composite T60 Regression and Classification Approach for Speech Dereverberation." IEEE/ACM Transactions on Audio, Speech, and Language Processing (2023).

• Yuchen Liu, Li-Chia Yang, Alexander Pawlicki, and Marko Stamenovic. "CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment}}." Proc. Interspeech 2022 (2022): 3318-3322.

• Yuchen Liu, Apu Kapadia, and Donald Williamson. "Preventing sensitive-word recognition using self-supervised learning to preserve user-privacy for automatic speech recognition}}." Proc. Interspeech 2022 (2022): 4207-4211.

• Yuchen Liu, Ziyu Xiang, Eun Ji Seong, Apu Kapadia, and Donald S. Williamson. "Defending Against Microphone-Based Attacks with Personalized Noise." Proceedings on Privacy Enhancing Technologies 2 (2021): 130-150.

• Yuying Li, Yuchen Liu, and Donald S. Williamson. "On Loss Functions for Deep-Learning Based T60 Estimation." In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 486-490. IEEE, 2021.

Full publication list can found here.