Yao Qian
Papers
1
Total Citations
38
H-Index
1
About
Yao Qian is a leading researcher in speech processing, with a primary focus on text-to-speech (TTS) synthesis, prosody modeling, and natural language processing. Her most cited work, "Automatic prosody prediction and detection with Conditional Random Field (CRF) models" (2010, 38 citations), tackles a persistent challenge in TTS: the "robotic" quality of synthesized speech. By applying CRF models, she advanced the automatic prediction and detection of prosodic boundaries and prominence, significantly improving the naturalness and expressiveness of synthetic voices. This contribution has been foundational for developing more human-like speech interfaces. Beyond this paper, Qian's research spans statistical parametric speech synthesis, voice conversion, and end-to-end TTS systems, often integrating machine learning techniques to bridge the gap between linguistic structure and acoustic realization. Her work has been widely cited by both academic researchers and industry practitioners working on voice user interfaces and assistive technologies. Through her innovative approaches to prosody, Yao Qian has helped shape modern TTS systems, making synthesized speech more fluid, expressive, and engaging for real-world applications.
Research Focus
Key Achievements
Top Papers
- 1