Picture for Chenda Li

Chenda Li

URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement

Add code
Jun 07, 2024
Viaarxiv icon

Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement

Add code
Jun 06, 2024
Viaarxiv icon

SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition

Add code
Jan 31, 2024
Viaarxiv icon

Adapting Multi-Lingual ASR Models for Handling Multiple Talkers

May 30, 2023
Figure 1 for Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
Figure 2 for Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
Figure 3 for Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
Figure 4 for Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
Viaarxiv icon

Target Sound Extraction with Variable Cross-modality Clues

Add code
Mar 15, 2023
Figure 1 for Target Sound Extraction with Variable Cross-modality Clues
Figure 2 for Target Sound Extraction with Variable Cross-modality Clues
Figure 3 for Target Sound Extraction with Variable Cross-modality Clues
Figure 4 for Target Sound Extraction with Variable Cross-modality Clues
Viaarxiv icon

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Add code
Jul 19, 2022
Figure 1 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 2 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 3 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 4 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Viaarxiv icon

Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge

Feb 24, 2022
Figure 1 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Figure 2 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Figure 3 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Figure 4 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Viaarxiv icon

SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation

Feb 10, 2022
Figure 1 for SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation
Figure 2 for SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation
Figure 3 for SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation
Figure 4 for SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation
Viaarxiv icon

Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions

Add code
Oct 27, 2021
Figure 1 for Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
Figure 2 for Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
Figure 3 for Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
Viaarxiv icon

Dual-Path Modeling for Long Recording Speech Separation in Meetings

Feb 23, 2021
Figure 1 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Figure 2 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Figure 3 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Figure 4 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Viaarxiv icon