Trainable Adaptive Window Switching for Speech Enhancement

TL;DR

This paper introduces a trainable adaptive window switching method integrated with DNNs for speech enhancement, optimizing time-frequency resolution dynamically to improve signal quality over fixed methods.

Contribution

It presents a novel trainable AWS technique that adjusts window lengths in real-time within a DNN framework for enhanced speech signal recovery.

Findings

Achieved higher signal-to-distortion ratio than fixed-resolution methods.

Demonstrated improved speech quality in DNN-based enhancement.

Validated effectiveness in real-world noisy environments.

Abstract

This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To recover the target signal precisely, DNN-based short-time frequency transforms have recently been investigated and used instead of the STFT. However, since such a fixed-resolution short-time frequency transform method has a T-F resolution problem based on the uncertainty principle, not only the short-time frequency transform but also the length of the windowing function should be optimized. To overcome this problem, we incorporate AWS into the speech enhancement procedure, and the windowing function of each time-frame is manipulated using a DNN depending on the input signal. We confirmed that the proposed method achieved a higher signal-to-distortion ratio than conventional speech enhancement methods in fixed-resolution frequency domains.