Zhen Ye
Scholar

Zhen Ye

Google Scholar ID: h7nrWb4AAAAJ
The Hong Kong University Of Science And Technology
Audio GenerationSpeech Synthesis
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
364
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
0
 
Contact
TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
2026
Cited
0
EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding
2026
Cited
0
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
2026
Cited
0
Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking
arXiv.org · 2026
Cited
0
Resume
Academic Achievements
  • Publications:
  • - LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
  • - Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model (AAAI 2025)
  • - CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model (ACM MM 2023)
  • - FlashSpeech: Efficient Zero-Shot (ACM MM 2024)
Research Experience
  • No specific work experience or research projects provided.
Education
  • PhD student at HKUST.
Background
  • Research Interests: LLM and speech synthesis.
Miscellany
  • No additional personal information provided.