Signal segmentation and its application in the feature extraction of speech

Speech is considered as a time-varying signal since the parameters of the signal such as the amplitude, frequency and phase varies in time. Segmenting a duration of captured speech into analysis frames of 20 msecs ensures the assumption of stationarity. If a captured speech segment representing a wo...

Full description

Bibliographic Details
Main Authors: Abdul Rahman, Ahmad Idil, Shaikh Salleh, Sheikh Hussain, Sha’ameri, Ahmad Zuri, AI-Attas, Syed Abdul Rahman
Format: Article
Language:English
Published: 2000
Subjects:
Online Access:http://eprints.utm.my/2300/
http://eprints.utm.my/2300/1/Rahman2000__SignalSegmentationandItsApplication.pdf
_version_ 1848890337742815232
author Abdul Rahman, Ahmad Idil
Shaikh Salleh, Sheikh Hussain
Sha’ameri, Ahmad Zuri
AI-Attas, Syed Abdul Rahman
author_facet Abdul Rahman, Ahmad Idil
Shaikh Salleh, Sheikh Hussain
Sha’ameri, Ahmad Zuri
AI-Attas, Syed Abdul Rahman
author_sort Abdul Rahman, Ahmad Idil
building UTeM Institutional Repository
collection Online Access
description Speech is considered as a time-varying signal since the parameters of the signal such as the amplitude, frequency and phase varies in time. Segmenting a duration of captured speech into analysis frames of 20 msecs ensures the assumption of stationarity. If a captured speech segment representing a word that may last for 600 msec, then a total of 30 analysis frames are required to the word. Due to the possibility that adjacent frames are identical, then it would be of interest to combine these frames into a single long frame. The interval where adjacent frames have identical parameters is referred as the time-invariant interval (TII). It is of interest to determine these intervals and two methods presented are the instantaneous energy and frequency estimation (IEFE) and localized time correlation (LTC) function. A comparison is made in the accuracy in the TII estimate for a set of speech samples
first_indexed 2025-11-15T20:40:28Z
format Article
id utm-2300
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:40:28Z
publishDate 2000
recordtype eprints
repository_type Digital Repository
spelling utm-23002010-06-01T03:02:23Z http://eprints.utm.my/2300/ Signal segmentation and its application in the feature extraction of speech Abdul Rahman, Ahmad Idil Shaikh Salleh, Sheikh Hussain Sha’ameri, Ahmad Zuri AI-Attas, Syed Abdul Rahman TK Electrical engineering. Electronics Nuclear engineering Speech is considered as a time-varying signal since the parameters of the signal such as the amplitude, frequency and phase varies in time. Segmenting a duration of captured speech into analysis frames of 20 msecs ensures the assumption of stationarity. If a captured speech segment representing a word that may last for 600 msec, then a total of 30 analysis frames are required to the word. Due to the possibility that adjacent frames are identical, then it would be of interest to combine these frames into a single long frame. The interval where adjacent frames have identical parameters is referred as the time-invariant interval (TII). It is of interest to determine these intervals and two methods presented are the instantaneous energy and frequency estimation (IEFE) and localized time correlation (LTC) function. A comparison is made in the accuracy in the TII estimate for a set of speech samples 2000-09-25 Article PeerReviewed application/pdf en http://eprints.utm.my/2300/1/Rahman2000__SignalSegmentationandItsApplication.pdf Abdul Rahman, Ahmad Idil and Shaikh Salleh, Sheikh Hussain and Sha’ameri, Ahmad Zuri and AI-Attas, Syed Abdul Rahman (2000) Signal segmentation and its application in the feature extraction of speech. TENCON 2000. Proceedings , 1 . pp. 265-270.
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Abdul Rahman, Ahmad Idil
Shaikh Salleh, Sheikh Hussain
Sha’ameri, Ahmad Zuri
AI-Attas, Syed Abdul Rahman
Signal segmentation and its application in the feature extraction of speech
title Signal segmentation and its application in the feature extraction of speech
title_full Signal segmentation and its application in the feature extraction of speech
title_fullStr Signal segmentation and its application in the feature extraction of speech
title_full_unstemmed Signal segmentation and its application in the feature extraction of speech
title_short Signal segmentation and its application in the feature extraction of speech
title_sort signal segmentation and its application in the feature extraction of speech
topic TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.utm.my/2300/
http://eprints.utm.my/2300/1/Rahman2000__SignalSegmentationandItsApplication.pdf