Cover Image

Mobile microphone robust acoustic feature identifcation using coefcient of variance

One of the most challenging techniques for speech analysis applications in mobile phones is acoustic feature extraction. The adverse environment noises, diversity of microphone specifications, and various recording software have a significant effect on the values of the extracted acous...

Full description

Saved in:
Bibliographic Details
Main Authors: Nik Hashim, Nik Nur Wahidah, Ahmed Ezzi, Mugahed Al Ezzi, Wilkes, Mitch D.
Format: Article
Language:English
Published: Springer 2021
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://irep.iium.edu.my/94266/9/94266_Mobile%20microphone%20robust%20acoustic%20feature%20identifcation%20using%20coefcient%20of%20variance.pdf
http://irep.iium.edu.my/94266/
https://doi.org/10.1007/s10772-021-09877-1
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.iium.irep.94266
record_format dspace
spelling my.iium.irep.942662021-12-02T05:32:27Z http://irep.iium.edu.my/94266/ Mobile microphone robust acoustic feature identifcation using coefcient of variance Nik Hashim, Nik Nur Wahidah Ahmed Ezzi, Mugahed Al Ezzi Wilkes, Mitch D. TK Electrical engineering. Electronics Nuclear engineering One of the most challenging techniques for speech analysis applications in mobile phones is acoustic feature extraction. The adverse environment noises, diversity of microphone specifications, and various recording software have a significant effect on the values of the extracted acoustic features. In this study, we investigate the robustness of different types of acoustic features related to time-based, frequency-based, and sustained vowel using 11 different mobile recording devices. 49 recordings of subjects reciting the Rainbow Passage and 25 recordings of sustained vowel /a/ were collected. By way of synchronous recording, we analyzed and compared the extracted 253-dimensional acoustic feature vectors in order to examine how consistent the data values between the different recording devices. The variability of data values was measured using the method of coefficient of variance. Data values with low variability were identified to be from features such as the transition parameters, amplitude modulation, contrast, Chroma, mean fundamental frequency and formants. These groups of features turn out to be more reliable than others in their dependency on the recording device specifications. Springer 2021 Article PeerReviewed application/pdf en http://irep.iium.edu.my/94266/9/94266_Mobile%20microphone%20robust%20acoustic%20feature%20identifcation%20using%20coefcient%20of%20variance.pdf Nik Hashim, Nik Nur Wahidah and Ahmed Ezzi, Mugahed Al Ezzi and Wilkes, Mitch D. (2021) Mobile microphone robust acoustic feature identifcation using coefcient of variance. International Journal of Speech Technology, 24. pp. 1089-1100. ISSN 1381-2416 E-ISSN 1572-8110 https://doi.org/10.1007/s10772-021-09877-1 10.1007/s10772-021-09877-1
institution Universiti Islam Antarabangsa Malaysia
building IIUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider International Islamic University Malaysia
content_source IIUM Repository (IREP)
url_provider http://irep.iium.edu.my/
language English
topic TK Electrical engineering. Electronics Nuclear engineering
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Nik Hashim, Nik Nur Wahidah
Ahmed Ezzi, Mugahed Al Ezzi
Wilkes, Mitch D.
Mobile microphone robust acoustic feature identifcation using coefcient of variance
description One of the most challenging techniques for speech analysis applications in mobile phones is acoustic feature extraction. The adverse environment noises, diversity of microphone specifications, and various recording software have a significant effect on the values of the extracted acoustic features. In this study, we investigate the robustness of different types of acoustic features related to time-based, frequency-based, and sustained vowel using 11 different mobile recording devices. 49 recordings of subjects reciting the Rainbow Passage and 25 recordings of sustained vowel /a/ were collected. By way of synchronous recording, we analyzed and compared the extracted 253-dimensional acoustic feature vectors in order to examine how consistent the data values between the different recording devices. The variability of data values was measured using the method of coefficient of variance. Data values with low variability were identified to be from features such as the transition parameters, amplitude modulation, contrast, Chroma, mean fundamental frequency and formants. These groups of features turn out to be more reliable than others in their dependency on the recording device specifications.
format Article
author Nik Hashim, Nik Nur Wahidah
Ahmed Ezzi, Mugahed Al Ezzi
Wilkes, Mitch D.
author_facet Nik Hashim, Nik Nur Wahidah
Ahmed Ezzi, Mugahed Al Ezzi
Wilkes, Mitch D.
author_sort Nik Hashim, Nik Nur Wahidah
title Mobile microphone robust acoustic feature identifcation using coefcient of variance
title_short Mobile microphone robust acoustic feature identifcation using coefcient of variance
title_full Mobile microphone robust acoustic feature identifcation using coefcient of variance
title_fullStr Mobile microphone robust acoustic feature identifcation using coefcient of variance
title_full_unstemmed Mobile microphone robust acoustic feature identifcation using coefcient of variance
title_sort mobile microphone robust acoustic feature identifcation using coefcient of variance
publisher Springer
publishDate 2021
url http://irep.iium.edu.my/94266/9/94266_Mobile%20microphone%20robust%20acoustic%20feature%20identifcation%20using%20coefcient%20of%20variance.pdf
http://irep.iium.edu.my/94266/
https://doi.org/10.1007/s10772-021-09877-1
_version_ 1718925635503521792
score 13.211869

Similar Items