Zhengqi Wen
Papers
1
Total Citations
5
H-Index
1
About
Zhengqi Wen is a leading researcher in speech and audio generation, with a primary focus on expressive text-to-speech (TTS) and emotional audio synthesis. His work addresses the critical gap between high-quality synthetic speech and the nuanced, emotionally resonant communication required for human-like interaction. Wen’s major contributions center on advancing TTS beyond mere intelligibility, tackling the challenge of conveying complex emotions and controlled, detailed content in generated audio. His involvement in organizing the ICAGC 2024 (Inspirational and Convincing Audio Generation Challenge) underscores his leadership in pushing the field toward more captivating and believable synthetic voices. This challenge, part of the ISCSLP 2024 Competitions track, directly confronts the limitations of current TTS technology. While his most cited paper is recent, its role in defining a key research challenge signals his growing influence. Wen’s work is foundational for applications in virtual assistants, audiobooks, and accessibility tools, where emotional authenticity is paramount. His research promises to make machines not just speak, but truly communicate.
Research Focus
Key Achievements
Top Papers
- 1ICAGC 2024: Inspirational and Convincing Audio Generation Challenge 20245 citations · 2024