Picture for Rongzhi Gu

Rongzhi Gu

Gull: A Generative Multifunctional Audio Codec

Add code
Apr 07, 2024
Viaarxiv icon

SECap: Speech Emotion Captioning with Large Language Model

Add code
Dec 23, 2023
Viaarxiv icon

ReZero: Region-customizable Sound Extraction

Add code
Aug 31, 2023
Viaarxiv icon

Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression

Add code
Aug 21, 2023
Viaarxiv icon

The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track

Add code
Aug 14, 2023
Viaarxiv icon

Fast Random Approximation of Multi-channel Room Impulse Response

Add code
Apr 17, 2023
Viaarxiv icon

3D Neural Beamforming for Multi-channel Speech Separation Against Location Uncertainty

Add code
Feb 27, 2023
Viaarxiv icon

Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation

Add code
Dec 24, 2022
Viaarxiv icon

Probing Deep Speaker Embeddings for Speaker-related Tasks

Add code
Dec 14, 2022
Figure 1 for Probing Deep Speaker Embeddings for Speaker-related Tasks
Figure 2 for Probing Deep Speaker Embeddings for Speaker-related Tasks
Figure 3 for Probing Deep Speaker Embeddings for Speaker-related Tasks
Figure 4 for Probing Deep Speaker Embeddings for Speaker-related Tasks
Viaarxiv icon

High Fidelity Speech Enhancement with Band-split RNN

Add code
Dec 01, 2022
Viaarxiv icon