HQY
|
- Professor
- Name (Pinyin):HQY
- Date of Employment:2005-04-29
- School/Department:信息学院
- Education Level:博士研究生毕业
- Degree:Doctor of Philosophy (PhD)
- Professional Title:Professor
- Status:在职
- Teacher College:School of Information
Contact Information
- Email：
- Paper Publications
- 基于预训练模型的半监督说话人验证系统.清华大学学报(自然科学版),2024,1-8.
- 面向闽南方言的自监督模型迁移学习.厦门大学学报(自然科学版),2024,63(04):687-693.
- HQY.THE XMUSPEECH SYSTEM FOR AUDIO-VISUAL TARGET SPEAKER EXTRACTION IN MISP 2023 CHALLENGE<bold> </bold>.2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings,39-40.
- HQY.DYNAMIC LANGUAGE GROUP-BASED MOE: ENHANCING EFFICIENCY AND FLEXIBILITY FOR CODE-SWITCHING SPEECH RECOGNITION.arXiv,2024,
- HQY,LL,MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis.THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 16,18117-18125.
- HQY.LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation.arXiv,2024,
- HQY.IMPROVING MULTI-SPEAKER ASR WITH OVERLAP-AWARE ENCODING AND MONOTONIC ATTENTION.ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,12416-12420.
- HQY.MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis.Proceedings of the AAAI Conference on Artificial Intelligence,2024,38(16):18117-18125.
- HQY.COMMUNITY DETECTION GRAPH CONVOLUTIONAL NETWORK FOR OVERLAP-AWARE SPEAKER DIARIZATION.arXiv,2023,
- HQY.Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge.arXiv,2023,