Haohe Liu
Scholar

Haohe Liu

Google Scholar ID: g3O4lJMAAAAJ
Research Scientist at Meta AI
Audio GenerationAudio ClassificationSpeech Quality EnhancementMusic Source Separation
Citations & Impact
All-time
Citations
3,723
 
H-index
27
 
i10-index
46
 
Publications
20
 
Co-authors
24
list available
Resume (English only)
Academic Achievements
  • First author of several papers including AudioLDM, AudioLDM2, NaturalSpeech, VoiceFixer, SemantiCodec, MusicLDM, AudioSR, etc., with around 3000 citations. Open-source projects/checkpoints on GitHub have received over 9500 stars. Received the Best Technical Paper Award at the 159th AES Convention. Published in IEEE/ACM Transactions on Audio, Speech, and Language Processing, IEEE Transactions on Automation Science and Engineering, Reviews in Aquaculture, and more.
Research Experience
  • Research Scientist at Meta. Member of the EPSRC AI for Sound Project (EP/T019751/1).
Education
  • PhD student at the Centre for Vision Speech and Signal Processing (CVSSP), University of Surrey. Supervised by Prof. Mark D. Plumbley and co-supervised by Prof. Wenwu Wang. Jointly funded by BBC R&D and the Doctoral College.
Background
  • Research interests include audio generative models, source separation, quality enhancement, and recognition. Published papers in journals and conferences such as TPAMI, TASLP, JSTSP, ICML, AAAI, NeurIPS, INTERSPEECH, and ICASSP.
Miscellany
  • Personal interests not mentioned