Picture for Huan Zhou

Huan Zhou

XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognition

Add code
Aug 20, 2024
Viaarxiv icon

MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition

Add code
May 06, 2024
Viaarxiv icon

Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder

Add code
Apr 08, 2024
Viaarxiv icon

Exploiting Low-level Representations for Ultra-Fast Road Segmentation

Add code
Feb 06, 2024
Viaarxiv icon

BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition

Add code
Oct 08, 2023
Viaarxiv icon

X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion

Add code
Mar 09, 2023
Viaarxiv icon

Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings

Add code
Jan 16, 2023
Viaarxiv icon

CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction

Add code
Jan 07, 2023
Viaarxiv icon

Joint Speech Activity and Overlap Detection with Multi-Exit Architecture

Add code
Sep 24, 2022
Figure 1 for Joint Speech Activity and Overlap Detection with Multi-Exit Architecture
Figure 2 for Joint Speech Activity and Overlap Detection with Multi-Exit Architecture
Figure 3 for Joint Speech Activity and Overlap Detection with Multi-Exit Architecture
Figure 4 for Joint Speech Activity and Overlap Detection with Multi-Exit Architecture
Viaarxiv icon

Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations

Add code
Sep 24, 2022
Figure 1 for Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations
Figure 2 for Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations
Figure 3 for Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations
Figure 4 for Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations
Viaarxiv icon