Log In Sign Up

Improving Speech Enhancement through Fine-Grained Speech Characteristics

by   Muqiao Yang, et al.

While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and can sound unnatural. We propose a novel approach to speech enhancement aimed at improving perceptual quality and naturalness of enhanced signals by optimizing for key characteristics of speech. We first identify key acoustic parameters that have been found to correlate well with voice quality (e.g. jitter, shimmer, and spectral flux) and then propose objective functions which are aimed at reducing the difference between clean speech and enhanced speech with respect to these features. The full set of acoustic features is the extended Geneva Acoustic Parameter Set (eGeMAPS), which includes 25 different attributes associated with perception of speech. Given the non-differentiable nature of these feature computation, we first build differentiable estimators of the eGeMAPS and then use them to fine-tune existing speech enhancement systems. Our approach is generic and can be applied to any existing deep learning based enhancement systems to further improve the enhanced speech signals. Experimental results conducted on the Deep Noise Suppression (DNS) Challenge dataset shows that our approach can improve the state-of-the-art deep learning based enhancement systems.


page 1

page 2

page 3

page 4


Phonetic Feedback for Speech Enhancement With and Without Parallel Speech Data

While deep learning systems have gained significant ground in speech enh...

Acoustic Structure Inverse Design and Optimization Using Deep Learning

From ancient to modern times, acoustic structures have been used to cont...

Processing Phoneme Specific Segments for Cleft Lip and Palate Speech Enhancement

The cleft lip and palate (CLP) speech intelligibility is distorted due t...

Coarse-to-fine Optimization for Speech Enhancement

In this paper, we propose the coarse-to-fine optimization for the task o...

Stable Training of DNN for Speech Enhancement based on Perceptually-Motivated Black-Box Cost Function

Improving subjective sound quality of enhanced signals is one of the mos...

Controlling the Perceived Sound Quality for Dialogue Enhancement with Deep Learning

Speech enhancement attenuates interfering sounds in speech signals but m...

AudVowelConsNet: A Phoneme-Level Based Deep CNN Architecture for Clinical Depression Diagnosis

Depression is a common and serious mood disorder that negatively affects...