A lip geometry approach for feature-fusion based audio-visual speech recognition
This paper describes a feature-fusion audio-visual speech recognition (AVSR) system that extracts lip geometry from the mouth region using a combination of skin color filter, border following and convex hull, and classification using a Hidden Markov Model. By defining a small number of highly descri...
Main Authors: | , |
---|---|
Format: | Conference or Workshop Item |
Language: | English English |
Published: |
IEEE
2014
|
Subjects: | |
Online Access: | http://umpir.ump.edu.my/id/eprint/29900/1/A%20lip%20geometry%20approach%20for%20feature-fusion%20based%20audio.pdf http://umpir.ump.edu.my/id/eprint/29900/2/A%20lip%20geometry%20approach%20for%20feature-fusion%20based%20audio_FULL.pdf |
_version_ | 1825813597425500160 |
---|---|
author | M. Z., Ibrahim Mulvaney, D. J. |
author_facet | M. Z., Ibrahim Mulvaney, D. J. |
author_sort | M. Z., Ibrahim |
collection | UMP |
description | This paper describes a feature-fusion audio-visual speech recognition (AVSR) system that extracts lip geometry from the mouth region using a combination of skin color filter, border following and convex hull, and classification using a Hidden Markov Model. By defining a small number of highly descriptive geometrical features relevant to the recognition task, the approach avoids the poor scalability (termed the `curse of dimensionality') that is often associated with featurefusion AVSR methods. The paper describes comparisons of the new approach with conventional appearance-based methods, namely the discrete cosine transform and the principal component analysis techniques, when operating under simulated ambient noise conditions that affect the spoken phrases. The experimental results demonstrate that, in the presence of audio noise, the geometrical method significantly improves speech recognition accuracy compared with appearance-based approaches, despite the new method requiring significantly fewer features. |
first_indexed | 2024-03-06T12:46:23Z |
format | Conference or Workshop Item |
id | UMPir29900 |
institution | Universiti Malaysia Pahang |
language | English English |
last_indexed | 2024-03-06T12:46:23Z |
publishDate | 2014 |
publisher | IEEE |
record_format | dspace |
spelling | UMPir299002022-12-28T04:07:45Z http://umpir.ump.edu.my/id/eprint/29900/ A lip geometry approach for feature-fusion based audio-visual speech recognition M. Z., Ibrahim Mulvaney, D. J. TK Electrical engineering. Electronics Nuclear engineering This paper describes a feature-fusion audio-visual speech recognition (AVSR) system that extracts lip geometry from the mouth region using a combination of skin color filter, border following and convex hull, and classification using a Hidden Markov Model. By defining a small number of highly descriptive geometrical features relevant to the recognition task, the approach avoids the poor scalability (termed the `curse of dimensionality') that is often associated with featurefusion AVSR methods. The paper describes comparisons of the new approach with conventional appearance-based methods, namely the discrete cosine transform and the principal component analysis techniques, when operating under simulated ambient noise conditions that affect the spoken phrases. The experimental results demonstrate that, in the presence of audio noise, the geometrical method significantly improves speech recognition accuracy compared with appearance-based approaches, despite the new method requiring significantly fewer features. IEEE 2014 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/29900/1/A%20lip%20geometry%20approach%20for%20feature-fusion%20based%20audio.pdf pdf en http://umpir.ump.edu.my/id/eprint/29900/2/A%20lip%20geometry%20approach%20for%20feature-fusion%20based%20audio_FULL.pdf M. Z., Ibrahim and Mulvaney, D. J. (2014) A lip geometry approach for feature-fusion based audio-visual speech recognition. In: 6th International Symposium on Communications, Control and Signal Processing, ISCCSP 2014 , 21 - 23 May 2014 , Athens, Greece. pp. 644-647. (6877957). ISBN 9781479928903 (Published) https://doi.org/10.1109/ISCCSP.2014.6877957 |
spellingShingle | TK Electrical engineering. Electronics Nuclear engineering M. Z., Ibrahim Mulvaney, D. J. A lip geometry approach for feature-fusion based audio-visual speech recognition |
title | A lip geometry approach for feature-fusion based audio-visual speech recognition |
title_full | A lip geometry approach for feature-fusion based audio-visual speech recognition |
title_fullStr | A lip geometry approach for feature-fusion based audio-visual speech recognition |
title_full_unstemmed | A lip geometry approach for feature-fusion based audio-visual speech recognition |
title_short | A lip geometry approach for feature-fusion based audio-visual speech recognition |
title_sort | lip geometry approach for feature fusion based audio visual speech recognition |
topic | TK Electrical engineering. Electronics Nuclear engineering |
url | http://umpir.ump.edu.my/id/eprint/29900/1/A%20lip%20geometry%20approach%20for%20feature-fusion%20based%20audio.pdf http://umpir.ump.edu.my/id/eprint/29900/2/A%20lip%20geometry%20approach%20for%20feature-fusion%20based%20audio_FULL.pdf |
work_keys_str_mv | AT mzibrahim alipgeometryapproachforfeaturefusionbasedaudiovisualspeechrecognition AT mulvaneydj alipgeometryapproachforfeaturefusionbasedaudiovisualspeechrecognition AT mzibrahim lipgeometryapproachforfeaturefusionbasedaudiovisualspeechrecognition AT mulvaneydj lipgeometryapproachforfeaturefusionbasedaudiovisualspeechrecognition |