Qiong Yang
Papers
1
Total Citations
18
H-Index
1
About
Dr. Qiong Yang is a leading researcher at the forefront of multimodal machine learning, with a primary focus on lip-to-speech (LTS) generation and generative adversarial networks (GANs). Her most influential work, "Integrated visual transformer and flash attention for lip-to-speech generation GAN" (2024), has already garnered 18 citations, highlighting its rapid impact on this emerging field. Dr. Yang addresses the critical challenge of converting silent facial movements into intelligible speech—a technology with transformative potential for assisting individuals with speech impairments and enhancing human-computer interaction in virtual assistants and robots. By integrating visual transformers with flash attention mechanisms, she has significantly improved the temporal coherence and audio quality of generated speech, pushing the boundaries of what is possible in LTS systems. Her contributions are notable for bridging computer vision and natural language processing, offering a robust framework that balances computational efficiency with high-fidelity output. Dr. Yang’s work is widely recognized for its practical applications and theoretical depth, making her a pivotal figure in advancing accessible communication technologies.
Research Focus
Key Achievements
Top Papers
- 1