ISCAS | Abdullah S, Zamani M, Demosthenous A | A real-time discrete wavelet transform-based adaptive voice activity detector and sub-band selection for feature extraction are proposed for noise cla...
A discrete wavelet transform-based voice activity detection and noise classification with sub-band selection
Abstract
A real-time discrete wavelet transform-based adaptive voice activity detector and sub-band selection for feature extraction are proposed for noise classification, which can be used in a speech processing pipeline. The voice activity detection and sub-band selection rely on wavelet energy features and the feature extraction process involves the extraction of mel-frequency cepstral coefficients from selected wavelet sub-bands and mean absolute values of all sub-bands. The method combined with a feedforward neural network with two hidden layers could be added to speech enhancement systems and deployed in hearing devices such as cochlear implants. In comparison to the conventional short-time Fourier transform-based technique, it has higher F1 scores and classification accuracies (with a mean of 0.916 and 90.1%, respectively) across five different noise types (babble, factory, pink, Volvo (car) and white noise), a significantly smaller feature set with 21 features, reduced memory requirement, faster training convergence and about half the computational cost.
Publication Type: | Conference |
---|
Authors: | Abdullah S, Zamani M, Demosthenous A |
---|
Publisher: | IEEE |
---|
Publication date: | 27/04/2021 |
---|
Volume: | 2021-May |
---|
Name of Conference: | 2020 IEEE International Symposium on Circuits and Systems (ISCAS) |
---|
ISBN-13: | 9781728192017 |
---|
Print ISSN: | 2158-1525 |
---|
DOI: | |
---|
Full Text URL: | |
---|
Explore how °×С½ãÂÛ̳ research is advancing the future technologies of a connected world: