已发表成果:
WOK 论文 83 篇;中文核心 12 篇;其它论文 1 篇;专利发明 6 个;
REFLOW-TTS: A RECTIFIED FLOW MODEL FOR HIGH-FIDELITY TEXT-TO-SPEECH
COMMUNITY DETECTION GRAPH CONVOLUTIONAL NETWORK FOR OVERLAP-AWARE SPEAKER DIARIZATION
Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge
Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge
Cross-Modal Semantic Alignment before Fusion for Two-Pass End-to-End Spoken Language Understanding
Conformer-based Language Embedding with Self-Knowledge Distillation for Spoken Language Identification
Meta Learning with Adaptive Loss Weight for Low-Resource Speech Recognition
Unsupervised Speaker Verification Using Pre-Trained Model and Label Correction
Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization
The XMU System for Audio-Visual Diarization and Recognition in MISP Challenge 2022
Towards A Unified Conformer Structure: from ASR to ASV Task
CASA-Net: Cross-attention and Self-attention for End-to-End Audio-visual Speaker Diarization
A Pipelined Framework with?Serialized Output Training for?Overlapping Speech Recognition