Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment
Humans are often able to compensate for noise degradation and uncertainty in speech information by augmenting the received audio with visual information. Such bimodal perception generates a rich combination of information that can be used in the recognition of speech. However, due to wide variabilit...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Asian Research Publishing Network (ARPN)
2015
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/12890/ http://umpir.ump.edu.my/id/eprint/12890/ http://umpir.ump.edu.my/id/eprint/12890/1/jeas_1215_3203.pdf http://umpir.ump.edu.my/id/eprint/12890/7/fkee-2015-zamri-Feature-Fusion%20based%20Audio-Visual.pdf |
| id |
ump-12890 |
|---|---|
| recordtype |
eprints |
| spelling |
ump-128902018-03-20T06:51:39Z http://umpir.ump.edu.my/id/eprint/12890/ Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment M. Z., Ibrahim Mulvaney, D. J. M. F., Abas TK Electrical engineering. Electronics Nuclear engineering Humans are often able to compensate for noise degradation and uncertainty in speech information by augmenting the received audio with visual information. Such bimodal perception generates a rich combination of information that can be used in the recognition of speech. However, due to wide variability in the lip movement involved in articulation, not all speech can be substantially improved by audio-visual integration. 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. The comparison of the new approach with conventional audio-only system is made when operating under simulated ambient noise conditions that affect the spoken phrases. The experimental results demonstrate that, in the presence of audio noise, the audio-visual approach significantly improves speech recognition accuracy compared with audio-only approach. Asian Research Publishing Network (ARPN) 2015-12-19 Article PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/12890/1/jeas_1215_3203.pdf application/pdf en http://umpir.ump.edu.my/id/eprint/12890/7/fkee-2015-zamri-Feature-Fusion%20based%20Audio-Visual.pdf M. Z., Ibrahim and Mulvaney, D. J. and M. F., Abas (2015) Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment. ARPN Journal of Engineering and Applied Sciences, 10 (23). pp. 17521-17527. ISSN 1819-6608 http://www.arpnjournals.org/jeas/research_papers/rp_2015/jeas_1215_3203.pdf |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
Universiti Malaysia Pahang |
| building |
UMP Institutional Repository |
| collection |
Online Access |
| language |
English English |
| topic |
TK Electrical engineering. Electronics Nuclear engineering |
| spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering M. Z., Ibrahim Mulvaney, D. J. M. F., Abas Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment |
| description |
Humans are often able to compensate for noise degradation and uncertainty in speech information by augmenting the received audio with visual information. Such bimodal perception generates a rich combination of information that can be used in the recognition of speech. However, due to wide variability in the lip movement involved in articulation, not all speech can be substantially improved by audio-visual integration. 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. The comparison of the new approach with conventional audio-only system is made when operating under simulated ambient noise conditions that affect the spoken phrases. The experimental results demonstrate that, in the presence of audio noise, the audio-visual approach significantly improves speech recognition accuracy compared with audio-only approach. |
| format |
Article |
| author |
M. Z., Ibrahim Mulvaney, D. J. M. F., Abas |
| author_facet |
M. Z., Ibrahim Mulvaney, D. J. M. F., Abas |
| author_sort |
M. Z., Ibrahim |
| title |
Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment |
| title_short |
Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment |
| title_full |
Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment |
| title_fullStr |
Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment |
| title_full_unstemmed |
Feature-Fusion based Audio-Visual Speech Recognition using Lip Geometry Features in Noisy Environment |
| title_sort |
feature-fusion based audio-visual speech recognition using lip geometry features in noisy environment |
| publisher |
Asian Research Publishing Network (ARPN) |
| publishDate |
2015 |
| url |
http://umpir.ump.edu.my/id/eprint/12890/ http://umpir.ump.edu.my/id/eprint/12890/ http://umpir.ump.edu.my/id/eprint/12890/1/jeas_1215_3203.pdf http://umpir.ump.edu.my/id/eprint/12890/7/fkee-2015-zamri-Feature-Fusion%20based%20Audio-Visual.pdf |
| first_indexed |
2023-09-18T22:14:54Z |
| last_indexed |
2023-09-18T22:14:54Z |
| _version_ |
1777415272119926784 |