Comprehensive design and development of time efficiency speaker recognition model from front end to back end
The rapid development of the forensic science technologies has been evolved speaker recognition to becoming one of the research topics. However, pattern classification from speech signal remains as challenging problem encountered in general speaker recognition system, including speaker verification...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTM Press
2008
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/10754/1/AbdulMananAhmad2008_ComprehensiveDesignAndDevelopmentOfTime.pdf |
| _version_ | 1825910546021482496 |
|---|---|
| author | Ahmad, Abdul Manan Loh, Mun Yee |
| author_facet | Ahmad, Abdul Manan Loh, Mun Yee |
| author_sort | Ahmad, Abdul Manan |
| collection | ePrints |
| description | The rapid development of the forensic science technologies has been evolved speaker recognition to becoming one of the research topics. However, pattern classification from speech signal remains as challenging problem encountered in general speaker recognition system, including speaker verification and speaker identification. Conventional speaker recognition researches are almost directed towards accuracy problems, not time processing problems. Due to the needs of reduction time processing of speaker recognition system, this research focuses on develop a comprehensive design of speaker recognition model from front end to back end which able to process speaker data in short time limit. In the front end process, we introduce some pre-processing techniques to enhance the speech signal. Whereas, for the back end process, we propose a decision function by using vector quantization techniques to decrease the training model for GMM in order to reduce the processing time. Experimental result shows that our hybrid VQ/GMM method always yielded better improvements in accuracy and bring almost 30% reduce in time processing. In this paper, a new, robust and simplicity computation method of pattern classification technique for speaker identification system is proposed. Consequently, this research is intended to develop a fully optimize ways speaker identification approach from hybrid modeling. |
| first_indexed | 2024-03-05T18:18:41Z |
| format | Article |
| id | utm.eprints-10754 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T18:18:41Z |
| publishDate | 2008 |
| publisher | Penerbit UTM Press |
| record_format | dspace |
| spelling | utm.eprints-107542017-11-01T04:17:21Z http://eprints.utm.my/10754/ Comprehensive design and development of time efficiency speaker recognition model from front end to back end Ahmad, Abdul Manan Loh, Mun Yee QA75 Electronic computers. Computer science The rapid development of the forensic science technologies has been evolved speaker recognition to becoming one of the research topics. However, pattern classification from speech signal remains as challenging problem encountered in general speaker recognition system, including speaker verification and speaker identification. Conventional speaker recognition researches are almost directed towards accuracy problems, not time processing problems. Due to the needs of reduction time processing of speaker recognition system, this research focuses on develop a comprehensive design of speaker recognition model from front end to back end which able to process speaker data in short time limit. In the front end process, we introduce some pre-processing techniques to enhance the speech signal. Whereas, for the back end process, we propose a decision function by using vector quantization techniques to decrease the training model for GMM in order to reduce the processing time. Experimental result shows that our hybrid VQ/GMM method always yielded better improvements in accuracy and bring almost 30% reduce in time processing. In this paper, a new, robust and simplicity computation method of pattern classification technique for speaker identification system is proposed. Consequently, this research is intended to develop a fully optimize ways speaker identification approach from hybrid modeling. Penerbit UTM Press 2008-12 Article PeerReviewed application/pdf en http://eprints.utm.my/10754/1/AbdulMananAhmad2008_ComprehensiveDesignAndDevelopmentOfTime.pdf Ahmad, Abdul Manan and Loh, Mun Yee (2008) Comprehensive design and development of time efficiency speaker recognition model from front end to back end. Jurnal Teknologi Maklumat, 20 (4). pp. 63-82. ISSN 0128-3790 |
| spellingShingle | QA75 Electronic computers. Computer science Ahmad, Abdul Manan Loh, Mun Yee Comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| title | Comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| title_full | Comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| title_fullStr | Comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| title_full_unstemmed | Comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| title_short | Comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| title_sort | comprehensive design and development of time efficiency speaker recognition model from front end to back end |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.utm.my/10754/1/AbdulMananAhmad2008_ComprehensiveDesignAndDevelopmentOfTime.pdf |
| work_keys_str_mv | AT ahmadabdulmanan comprehensivedesignanddevelopmentoftimeefficiencyspeakerrecognitionmodelfromfrontendtobackend AT lohmunyee comprehensivedesignanddevelopmentoftimeefficiencyspeakerrecognitionmodelfromfrontendtobackend |