UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

A discrete wavelet transform-based voice activity detection and noise classification with sub-band selection

Abdullah, S; Zamani, M; Demosthenous, A; (2021) A discrete wavelet transform-based voice activity detection and noise classification with sub-band selection. In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE: Daegu, Korea. Green open access

[thumbnail of Binti Abdullah_ISCAS_2021_Final_submission.pdf]
Preview
Text
Binti Abdullah_ISCAS_2021_Final_submission.pdf - Accepted Version

Download (718kB) | Preview

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.

Type: Proceedings paper
Title: A discrete wavelet transform-based voice activity detection and noise classification with sub-band selection
Event: 2021 IEEE International Symposium on Circuits and Systems (ISCAS)
ISBN-13: 9781728192017
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ISCAS51556.2021.9401647
Publisher version: https://doi.org/10.1109/ISCAS51556.2021.9401647
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Discrete wavelet transform, mel-frequency cepstral coefficients, multilayer perceptron, noise classification, sub-band selection, voice activity detection
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10131676
Downloads since deposit
85Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item