Shenghui Lu

According to our database1, Shenghui Lu authored at least 8 papers between 2024 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement.
CoRR, June, 2025

Pseudo Labels-based Neural Speech Enhancement for the AVSR Task in the MISP-Meeting Challenge.
CoRR, May, 2025

SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow.
CoRR, April, 2025

A Noisy Label Filter based on GMM Binary Classification for Speaker Verification.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Dynamic Language Group-based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024
Dynamic Language Group-Based MoE: Enhancing Efficiency and Flexibility for Code-Switching Speech Recognition.
CoRR, 2024

MinSpeech: A Corpus of Southern Min Dialect for Automatic Speech Recognition.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024


  Loading...