Multi-Domain Processing via Hybrid Denoising Networks for Speech EnhancementDownload PDF

Anonymous

22 Oct 2018 (modified: 05 May 2023)NIPS 2018 Workshop IRASL Blind SubmissionReaders: Everyone
Abstract: We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific representations such as raw-audio and spectrograms are each effective at targeting different types of noise. By integrating both approaches, our model can learn multi-scale and multi-domain features, effectively removing noise existing on different regions on the time-frequency space in a complementary way. Experimental results show that the proposed hybrid model yields better performance and robustness than using each model individually.
TL;DR: A hybrid model utilizing both raw-audio and spectrogram information for speech enhancement tasks.
Keywords: speech enhancement, multi-scale analysis, time-frequency domain, hybrid network
7 Replies

Loading