Toward Universal Speech Enhancement for Diverse Input Conditions
Abstract
The past decade has witnessed substantial growth of data-driven speech enhancement (SE) techniques thanks to deep learning. While existing approaches have shown impressive performance in some common datasets, most of them are designed only for a single condition (e.g., single-channel, multi-channel, or a fixed sampling frequency) or only consider a single task (e.g., denoising or dereverberation). Currently, there is no universal SE approach that can effectively handle diverse input conditions with a single model. In this paper, we make the first attempt to investigate this line of research. First, we devise a single SE model that is independent of microphone channels, signal lengths, and sampling frequencies. Second, we design a universal SE benchmark by combining existing public corpora with multiple conditions. Our experiments on a wide range of datasets show that the proposed single model can successfully handle diverse conditions with strong performance.
Cite
@article{arxiv.2309.17384,
title = {Toward Universal Speech Enhancement for Diverse Input Conditions},
author = {Wangyou Zhang and Kohei Saijo and Zhong-Qiu Wang and Shinji Watanabe and Yanmin Qian},
journal= {arXiv preprint arXiv:2309.17384},
year = {2024}
}
Comments
6 pages, 3 figures, 5 tables, published in ASRU 2023 (corrected the results of noisy speech on CHiME-4 (Simu) in Table 4)