Scholar
Xinhao Mei
Google Scholar ID: vGoCkeUAAAAJ
Meta
audio signal processing
machine learning
machine listening
multimodal learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,371
H-index
16
i10-index
21
Publications
20
Co-authors
21
list available
Contact
Email
meixinhao429@gmail.com
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
5 items
SongCraft: Unified Song Generation and Editing with Reconstructive Learning
2026
Cited
0
Exploring Audio Hallucination in Egocentric Video Understanding
2026
Cited
0
EgoAVU: Egocentric Audio-Visual Understanding
2026
Cited
0
SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training
2026
Cited
0
Lightweight and Generalizable Acoustic Scene Representations via Contrastive Fine-Tuning and Distillation
2025
Cited
0
Resume
Academic Achievements
- Two papers accepted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), June 2024
- Joined Meta as a research scientist, April 2024
- Achieved 2nd place in Task 5 of DCASE Challenge 2022 “Few-shot Bioacoustic Event Detection”, July 2022
- Achieved 2nd place in Task 6b of DCASE Challenge 2022 “Language-based Audio Retrieval”, July 2022
- Achieved 3rd place in Task 6a of DCASE Challenge 2022 “Automated Audio Captioning”, July 2022
- 2 papers accepted by InterSpeech 2022, June 2022
- 1 paper accepted by ICASSP 2022, January 2022
- Achieved 3rd place in Task 6 of DCASE Challenge 2021 “Automated Audio Captioning”, July 2021
Research Experience
- Research Scientist at Meta, 2024 - Present, Redmond, US
Education
- PhD in Vision, Speech and Signal Processing, University of Surrey (UK), 2021-2024, supervised by Prof. Wenwu Wang and Dr. Yunpeng Li
- MSc in Computer Vision, Robotics and Machine Learning, University of Surrey (UK), 2019-2020
- B.Eng in Software Engineering, Southwest Petroleum University (China), 2015-2019
Background
Research Interests: Cross-Modal Machine Learning, Audio Understanding and Generation. Currently a research scientist at Meta.
Co-authors
15 total
Wenwu Wang
Professor, University of Surrey, UK
Xubo Liu
Meta Superintelligence Labs
Haohe Liu
Research Scientist at Meta AI
Qiuqiang Kong
The Chinese University of Hong Kong
Qiushi Huang
University of Surrey
Tom Ko
ByteDance AI Lab Hong Kong
Yangyang Shi
Meta
Zhaoheng Ni
Meta Reality Labs