An acoustic-phonetic approach in automatic Arabic speech recognition

In a large vocabulary speech recognition system the broad phonetic classification technique is used instead of detailed phonetic analysis to overcome the variability in the acoustic realisation of utterances. The broad phonetic description of a word is used as a means of lexical access, where the le...

Full description

Saved in:
Bibliographic Details
Main Author: Marwan Al-Zabibi
Format: Default Thesis
Published: 1990
Subjects:
Online Access:https://hdl.handle.net/2134/6949
Tags: Add Tag
No Tags, Be the first to tag this record!
id rr-article-9539828
record_format Figshare
spelling rr-article-95398281990-01-01T00:00:00Z An acoustic-phonetic approach in automatic Arabic speech recognition Marwan Al-Zabibi (7203125) Mechanical engineering not elsewhere classified Linguistics Speech recognition Mechanical Engineering not elsewhere classified In a large vocabulary speech recognition system the broad phonetic classification technique is used instead of detailed phonetic analysis to overcome the variability in the acoustic realisation of utterances. The broad phonetic description of a word is used as a means of lexical access, where the lexicon is structured into sets of words sharing the same broad phonetic labelling. This approach has been applied to a large vocabulary isolated word Arabic speech recognition system. Statistical studies have been carried out on 10,000 Arabic words (converted to phonemic form) involving different combinations of broad phonetic classes. Some particular features of the Arabic language have been exploited. The results show that vowels represent about 43% of the total number of phonemes. They also show that about 38% of the words can uniquely be represented at this level by using eight broad phonetic classes. When introducing detailed vowel identification the percentage of uniquely specified words rises to 83%. These results suggest that a fully detailed phonetic analysis of the speech signal is perhaps unnecessary. In the adopted word recognition model, the consonants are classified into four broad phonetic classes, while the vowels are described by their phonemic form. A set of 100 words uttered by several speakers has been used to test the performance of the implemented approach. In the implemented recognition model, three procedures have been developed, namely voiced-unvoiced-silence segmentation, vowel detection and identification, and automatic spectral transition detection between phonemes within a word. The accuracy of both the V-UV-S and vowel recognition procedures is almost perfect. A broad phonetic segmentation procedure has been implemented, which exploits information from the above mentioned three procedures. Simple phonological constraints have been used to improve the accuracy of the segmentation process. The resultant sequence of labels are used for lexical access to retrieve the word or a small set of words sharing the same broad phonetic labelling. For the case of having more than one word-candidates, a verification procedure is used to choose the most likely one. 1990-01-01T00:00:00Z Text Thesis 2134/6949 https://figshare.com/articles/thesis/An_acoustic-phonetic_approach_in_automatic_Arabic_speech_recognition/9539828 CC BY-NC-ND 4.0
institution Loughborough University
collection Figshare
topic Mechanical engineering not elsewhere classified
Linguistics
Speech recognition
Mechanical Engineering not elsewhere classified
spellingShingle Mechanical engineering not elsewhere classified
Linguistics
Speech recognition
Mechanical Engineering not elsewhere classified
Marwan Al-Zabibi
An acoustic-phonetic approach in automatic Arabic speech recognition
description In a large vocabulary speech recognition system the broad phonetic classification technique is used instead of detailed phonetic analysis to overcome the variability in the acoustic realisation of utterances. The broad phonetic description of a word is used as a means of lexical access, where the lexicon is structured into sets of words sharing the same broad phonetic labelling. This approach has been applied to a large vocabulary isolated word Arabic speech recognition system. Statistical studies have been carried out on 10,000 Arabic words (converted to phonemic form) involving different combinations of broad phonetic classes. Some particular features of the Arabic language have been exploited. The results show that vowels represent about 43% of the total number of phonemes. They also show that about 38% of the words can uniquely be represented at this level by using eight broad phonetic classes. When introducing detailed vowel identification the percentage of uniquely specified words rises to 83%. These results suggest that a fully detailed phonetic analysis of the speech signal is perhaps unnecessary. In the adopted word recognition model, the consonants are classified into four broad phonetic classes, while the vowels are described by their phonemic form. A set of 100 words uttered by several speakers has been used to test the performance of the implemented approach. In the implemented recognition model, three procedures have been developed, namely voiced-unvoiced-silence segmentation, vowel detection and identification, and automatic spectral transition detection between phonemes within a word. The accuracy of both the V-UV-S and vowel recognition procedures is almost perfect. A broad phonetic segmentation procedure has been implemented, which exploits information from the above mentioned three procedures. Simple phonological constraints have been used to improve the accuracy of the segmentation process. The resultant sequence of labels are used for lexical access to retrieve the word or a small set of words sharing the same broad phonetic labelling. For the case of having more than one word-candidates, a verification procedure is used to choose the most likely one.
format Default
Thesis
author Marwan Al-Zabibi
author_facet Marwan Al-Zabibi
author_sort Marwan Al-Zabibi (7203125)
title An acoustic-phonetic approach in automatic Arabic speech recognition
title_short An acoustic-phonetic approach in automatic Arabic speech recognition
title_full An acoustic-phonetic approach in automatic Arabic speech recognition
title_fullStr An acoustic-phonetic approach in automatic Arabic speech recognition
title_full_unstemmed An acoustic-phonetic approach in automatic Arabic speech recognition
title_sort acoustic-phonetic approach in automatic arabic speech recognition
publishDate 1990
url https://hdl.handle.net/2134/6949
_version_ 1794754773499510784