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...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | en en |
| Published: |
Asian Research Publishing Network (ARPN)
2015
|
| Subjects: | |
| Online Access: | 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 http://umpir.ump.edu.my/id/eprint/12890/ http://www.arpnjournals.org/jeas/research_papers/rp_2015/jeas_1215_3203.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1831523556898373632 |
|---|---|
| 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 |
| building | UMPSA Library |
| collection | Institutional Repository |
| content_provider | Universiti Malaysia Pahang Al-Sultan Abdullah |
| content_source | UMPSA Institutional Repository |
| continent | Asia |
| country | Malaysia |
| 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 |
| id | my.ump.umpir.12890 |
| institution | Universiti Malaysia Pahang |
| language | en en |
| publishDate | 2015 |
| publisher | Asian Research Publishing Network (ARPN) |
| record_format | eprints |
| spelling | my.ump.umpir.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. (Published) http://www.arpnjournals.org/jeas/research_papers/rp_2015/jeas_1215_3203.pdf |
| 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 |
| title | 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_short | 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 |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | 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 http://umpir.ump.edu.my/id/eprint/12890/ http://www.arpnjournals.org/jeas/research_papers/rp_2015/jeas_1215_3203.pdf |
| url_provider | http://umpir.ump.edu.my/ |