Sorry, you need to enable JavaScript to visit this website.

USEE: UNIFIED SPEECH ENHANCEMENT AND EDITING WITH CONDITIONAL DIFFUSION MODELS

DOI:
10.60864/g9kv-eh42
Citation Author(s):
Muqiao Yang, Chunlei Zhang, Yong Xu, Zhongweiyang Xu, Heming Wang, Bhiksha Raj, Dong Yu
Submitted by:
Muqiao Yang
Last updated:
6 June 2024 - 10:54am
Document Type:
Poster
Document Year:
2024
Presenters:
Muqiao Yang
 

Speech enhancement aims to improve the quality of speech signals in terms of quality and intelligibility, and speech editing refers to the process of editing the speech according to specific user needs. In this paper, we propose a Unified Speech Enhancement and Editing (uSee) model with conditional diffusion models to handle various tasks at the same time in a generative manner. Specifically, by providing multiple types of conditions including self-supervised learning embeddings and proper text prompts to the score-based diffusion model, we can enable controllable generation of the unified speech enhancement and editing model to perform corresponding actions on the source speech. Our experiments show that our proposed uSee model can achieve superior performance in both speech denoising and dereverberation compared to other related generative speech enhancement models, and can perform speech editing given desired environmental sound text description, signal-to-noise ratios (SNR), and room impulse responses (RIR).

up
0 users have voted: