CV

Research Scientist

NVIDIA NeMo

Project: Multimodal large language models, full-duplex speech-to-speech models

AI Research Intern

NVIDIA NeMo

Project: Speech-text language models with multi-turn mixed-modal chat capabilities

Research Scientist Intern

Meta AI (Fundamental AI Research, FAIR)

Project: Speech large language models for voice-preserved textless speech-to-speech translation

Speech Recognition Intern

ASAPP

Project: Speech model compression and encoder architecture design

Doctor of Philosophy in Electrical and Computer Engineering

Carnegie Mellon University

Advisor: Prof. Shinji Watanabe

Thesis: Towards effective and efficient open speech foundation models

Research areas: Speech foundation models, speech recognition

Open source: Contributor and maintainer of ESPnet

Bachelor of Engineering in Electronic Information Science and Technology

Tsinghua University

GPA: 3.96/4.00, Ranking: 2/262

Advisor: Prof. Liangrui Peng

Thesis: Deep learning-based semi-supervised transfer learning for handwritten text recognition

ISCA Award for Best Student Paper at INTERSPEECH 2025

International Speech Communication Association (ISCA)

For the first-authored paper: OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

IEEE SLT 2024 Best Paper Award

2024 IEEE Spoken Language Technology Workshop

For the paper: Contextualized Automatic Speech Recognition with Dynamic Vocabulary

EMNLP 2024 Best Paper Award

The 2024 Conference on Empirical Methods in Natural Language Processing

For the paper: Towards Robust Speech Representation Learning for Thousands of Languages

ICASSP 2023 Top 3% Paper Recognition

IEEE International Conference on Acoustics, Speech and Signal Processing

For two first-authored papers and one co-authored paper

SPIE Medical Imaging 2020 Best Student Paper Award Finalist

The International Society for Optics and Photonics (SPIE)

For first-authored paper: Microcalcification localization and cluster detection using unsupervised convolutional autoencoders and structural similarity index

Graduate Teaching Assistant

Carnegie Mellon University

Course:18-781/11-751 Speech Recognition and Understanding

Instructor: Prof. Shinji Watanabe

Graduate Teaching Assistant

Carnegie Mellon University

Course:18-781/11-751 Speech Recognition and Understanding

Instructor: Prof. Shinji Watanabe

Graduate Teaching Assistant

Carnegie Mellon University

Course:18-781/11-751 Speech Recognition and Understanding

Instructor: Prof. Shinji Watanabe

Graduate Teaching Assistant

Carnegie Mellon University

Course:18-781/11-751 Speech Recognition and Understanding

Instructor: Prof. Ian Lane and Prof. Shinji Watanabe