Lei Xie

DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matching

SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement

SongEval: A Benchmark Dataset for Song Aesthetics Evaluation

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling