pith. sign in

arxiv: 1910.12620 · v3 · pith:KG4OUPATnew · submitted 2019-10-21 · 📡 eess.AS · cs.LG· cs.NE· cs.SD· stat.ML

AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks

classification 📡 eess.AS cs.LGcs.NEcs.SDstat.ML
keywords speechenhancementsystemsadversarialdenoisingframeworkgenerativeother
0
0 comments X
read the original abstract

Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded environments. Thus, speech enhancement is a valuable building block in ASR systems and other applications such as hearing aids, smartphones and teleconferencing systems. In this paper, a generative adversarial network (GAN) based framework is investigated for the task of speech enhancement, more specifically speech denoising of audio tracks. A new architecture based on CasNet generator and an additional feature-based loss are incorporated to get realistically denoised speech phonetics. Finally, the proposed framework is shown to outperform other learning and traditional model-based speech enhancement approaches.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.