Yichen's Homepage

Hello! I am currently a Research Scientist at Anuttacon, where our work primarily focuses on audio understanding. I hold a Bachelor’s degree in Computer Science from the University of Illinois at Urbana-Champaign (UIUC) and a Master’s degree in Artificial Intelligence from Carnegie Mellon University (CMU). At CMU, I have been actively involved in research at the WAVLab under the supervision of Prof. Shinji Watanabe.

My core research interests include general speech/audio language models, audio-visual fusion, and multimodal language models.

During my undergraduate studies, I was also fortunate to work with Prof. Tarek Abdelzaher, Prof. Kris Hauser, and Prof. Yuxiong Wang, which greatly shaped my research journey.

Google Scholar  Github  Email  CV  LinkedIn  Ins 

News

• [01/2025] I joined Anuttacon as an Research Scientist focus on Audio Understanding!
• [12/2024] Graduated from CMU!
• [12/2024] One paper accepted by AAAI 2025
• [09/2024] FastAdaSP has been accepted by EMNLP2024!
• [07/2024] My first first-author paper has been accepted by Interspeech 2024 Syndata4genai Workshop!
• [01/2024] Released my first open source project: ViDove V0.1.0! See the official intro here
• [08/2023] Joined WAVLab as a research assistant
• [08/2023] Start my journey at CMU!
• [05/2023] Start my internship at Trova.AI, supervised by Sanjay Patel
• [05/2023] Graduated with the highest distinction from UIUC!
• [06/2022] Joined CyPhy Group as an undergraduate research assistant working on robust graph learning on dynamic link prediction.

Publications

• FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model
  Yichen Lu*, Jiaqi Song*, Chao-Han Huck Yang, Shinji Watanabe
  EMNLP 2024 Industry Track (Oral)
  Paper
  Blog
• Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization
  Yihan Wu, Yichen Lu, Yifan Peng, Xihua Wang, Ruihua Song, Shinji Watanabe
  AAAI 2025
  Paper
• SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data
  Yichen Lu*, Jiaqi Song*, Xuankai Chang, Hengwei Bian, Soumi Maiti, Shinji Watanabe
  Interspeech 2024 Syndata4genai Workshop
  Paper
• Robust Audiovisual Speech Recognition Models with Mixture-of-Experts
  Yihan Wu, Yifan Peng, Yichen Lu, Xuankai Chang, Ruihua Song, Shinji Watanabe
  SLT 2024
  Paper
• Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
  Xuankai Chang, Brian Yan, Kwanghee Choi, Jeeweon Jung, Yichen Lu, Soumi Maiti, Roshan Sharma, Jiatong Shi, Jinchuan Tian, Shinji Watanabe, Yuya Fujita, Takashi Maekaku, Pengcheng Guo, Yao-Fei Cheng, Pavel Denisov, Kohei Saijo, Hsiu-Hsuan Wang
  ICASSP 2024
  Paper
• Robust Reasoning Over Noisy Knowledge Graphs Via Structure Learning.
  Ruijie Wang, Baoyu Li, Yichen Lu, Tarek Abdelzaher.
  ACL Findings 2023
  Paper

Research Experiences

• [08/2023 - Present] WAVLab, supervised by Prof. Shinji Watanabe
• [06/2022 - 05/2023] CyPhy Group, supervised by Prof. Tarek Abdelazher
• [02/2022 - 08/2022] Intelligent Motion Lab, supervised by Prof. Kris Hauser and Prof. Yuxiong Wang

Internship Experiences

• [05/2023 - 08/2023] Machine Learning Engineer Intern at Trova.AI
• [07/2021 - 01/2022] Software Engineer Intern at VMware, Inc.
• [10/2020 - 02/2021] Software Engineer Intern at NetEase, Inc.