Title
Voicing detection based on adaptive aperiodicity thresholding for speech enhancement in non-stationary noise
Abstract
In this study, the authors present a novel voicing detection algorithm which employs the well-known aperiodicity measure to detect voiced speech in signals contaminated with non-stationary noise. The method computes a signal-adaptive decision threshold which takes into account the current noise level, enabling voicing detection by direct comparison with the extracted aperiodicity. This adaptive threshold is updated at each frame by making a simple estimate of the current noise power, and thus is adapted to fluctuating noise conditions. Once the aperiodicity is computed, the method only requires a small number of operations, and enables its implementation in challenging devices (such as hearing aids) if an efficient approximation of the difference function is employed to extract the aperiodicity. Evaluation over a database of speech sentences degraded by several types of noise reveals that the proposed voicing classifier is robust against different noises and signal-to-noise ratios. In addition, to evaluate the applicability of the method for speech enhancement, a simple F0-based speech enhancement algorithm integrating the proposed classifier is implemented. The system is shown to achieve competitive results, in terms of objective measures, when compared with other well-known speech enhancement approaches.
Year
DOI
Venue
2014
10.1049/iet-spr.2012.0224
IET Signal Processing
Keywords
Field
DocType
hearing aids,speech enhancement,adaptive aperiodicity thresholding,fluctuating noise,nonstationary noise,signal-adaptive decision,signal-to-noise ratios,speech sentences database,voicing classifier,voicing detection
Speech enhancement,Speech processing,Non stationary noise,Computer science,Speech enhancement algorithm,Speech recognition,Voice,Thresholding,Classifier (linguistics),Current noise
Journal
Volume
Issue
ISSN
8
2
1751-9675
Citations 
PageRank 
References 
1
0.35
13
Authors
5