Junyi Ao
Scholar

Junyi Ao

Google Scholar ID: eUiG0O0AAAAJ
The Chinese University of Hong Kong, Shenzhen
Speech RecognitionSelf-Supervised Learning
Citations & Impact
All-time
Citations
644
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
21
list available
Resume (English only)
Academic Achievements
  • USED: Universal Speaker Extraction and Diarization (TASLP 2024); SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words (NeurIPS 2024); Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks (IEEE Signal Processing Letters 2024); SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech (INTERSPEECH 2024); CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning (INTERSPEECH 2023); Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder (INTERSPEECH 2023); token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text (ICASSP 2023); Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data (INTERSPEECH 2022); SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing (ACL 2022); SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training (EMNLP 2022); LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT (INTERSPEECH 2022); The YiTrans Speech Translation System for IWSLT 2022 Offline Shared Task (ACL@IWSLT 2022); Multi-View Self-Attention Based Transformer for Speaker Recognition (ICASSP 2022); Improving Attention-based End-to-end ASR by Incorporating an N-gram Neural Network (ISCSLP 2021); Solla: Towards a Speech-Oriented LLM That Hears (Preprint)
Research Experience
  • 2025.05 - Present, Research Scientist Intern at Meta GenAI; 2024.03 - 2025.05, Research Intern at Bytedance, mentored by Prof. Zhizheng Wu and Dr. Xiaohai Tian; 2022.06 - 2022.12, Research Intern at Bytedance, mentored by Prof. Tom Ko; 2021.06 - 2022.04, Research Intern at MSRA NLC group, Beijing, mentored by Dr. Long Zhou and Dr. Shujie Liu; 2019.06 - 2019.08, Machine Learning Intern at Tencent, Shenzhen.
Education
  • 2022.09 - Present, PhD student at the School of Data Science, The Chinese University of Hong Kong, Shenzhen, supervised by Prof. Haizhou Li; 2016.09 - 2020.06, Bachelor's degree from Southern University of Science and Technology, supervised by Prof. Tom Ko.
Background
  • Research interests include automatic speech recognition, speech pre-training, and large language models. Published several papers in top international AI conferences and journals such as TASLP, NeurIPS, ACL, and ICASSP.