Lei Xie

9

Papers

189

Total Citations

Papers (9)

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

A Diffusion-Based Framework for Multi-Class Anomaly Detection

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

Drop the Beat! Freestyler for Accompaniment Conditioned Rapping Voice Generation

SignGraph: A Sign Sequence is Worth Graphs of Nodes

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations