Human computer interaction using isolated-words speech recognition technology
This research paper aims to develop an isolated-word automatic speech recognition (IWASR) system based on Vector Quantization (VQ). This system receives, analyzes, searches and matches an input speech signal with the trained set of speech signals which are stored in the database/codebook, and retu...
| Main Authors: | , , , |
|---|---|
| Format: | Proceeding Paper |
| Language: | English |
| Published: |
2007
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/5881/1/04658569.pdf |
| _version_ | 1796875317237776384 |
|---|---|
| author | Abu Shariah, Mohammad Abd-Alrahman Mahmoud Ainon, Raja Noor Zainuddin, Roziati Khalifa, Othman Omran |
| author_facet | Abu Shariah, Mohammad Abd-Alrahman Mahmoud Ainon, Raja Noor Zainuddin, Roziati Khalifa, Othman Omran |
| author_sort | Abu Shariah, Mohammad Abd-Alrahman Mahmoud |
| collection | IIUM |
| description | This research paper aims to develop an isolated-word
automatic speech recognition (IWASR) system based on Vector
Quantization (VQ). This system receives, analyzes, searches and matches an input speech signal with the trained set of speech signals which are stored in the database/codebook, and returns matching results to users. IWASR is meant to assist customers calling a university’s telephone operator to respond to their enquiries in a convenient way using their natural speech. Callers are assisted to select language, faculty and the staff name they wish to contact. To extract features from speech signals, Mel-Frequency Cepstral Coefficients (MFCC) algorithm was applied.
Subsequently, Vector Quantization was used for all feature
vectors generated from the MFCC. A codebook was resulted from training the VQ initial codebook and experimental results showed that the recognition rate has been improved with the increase of codebook size and showed that the codebook size of 81 feature vectors had a recognition rate exceeded 85%. |
| first_indexed | 2024-03-05T22:37:00Z |
| format | Proceeding Paper |
| id | oai:generic.eprints.org:5881 |
| institution | International Islamic University Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:37:00Z |
| publishDate | 2007 |
| record_format | dspace |
| spelling | oai:generic.eprints.org:58812011-11-21T22:36:51Z http://irep.iium.edu.my/5881/ Human computer interaction using isolated-words speech recognition technology Abu Shariah, Mohammad Abd-Alrahman Mahmoud Ainon, Raja Noor Zainuddin, Roziati Khalifa, Othman Omran T Technology (General) This research paper aims to develop an isolated-word automatic speech recognition (IWASR) system based on Vector Quantization (VQ). This system receives, analyzes, searches and matches an input speech signal with the trained set of speech signals which are stored in the database/codebook, and returns matching results to users. IWASR is meant to assist customers calling a university’s telephone operator to respond to their enquiries in a convenient way using their natural speech. Callers are assisted to select language, faculty and the staff name they wish to contact. To extract features from speech signals, Mel-Frequency Cepstral Coefficients (MFCC) algorithm was applied. Subsequently, Vector Quantization was used for all feature vectors generated from the MFCC. A codebook was resulted from training the VQ initial codebook and experimental results showed that the recognition rate has been improved with the increase of codebook size and showed that the codebook size of 81 feature vectors had a recognition rate exceeded 85%. 2007 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/5881/1/04658569.pdf Abu Shariah, Mohammad Abd-Alrahman Mahmoud and Ainon, Raja Noor and Zainuddin, Roziati and Khalifa, Othman Omran (2007) Human computer interaction using isolated-words speech recognition technology. In: 2007 International Conference on Intelligent & Advanced Systems (ICIAS) , 25-28 November, 2007, Kuala Lumpur Convention Centre. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4658569 doi:10.1109/ICIAS.2007.4658569 |
| spellingShingle | T Technology (General) Abu Shariah, Mohammad Abd-Alrahman Mahmoud Ainon, Raja Noor Zainuddin, Roziati Khalifa, Othman Omran Human computer interaction using isolated-words speech recognition technology |
| title | Human computer interaction using isolated-words speech recognition technology |
| title_full | Human computer interaction using isolated-words speech recognition technology |
| title_fullStr | Human computer interaction using isolated-words speech recognition technology |
| title_full_unstemmed | Human computer interaction using isolated-words speech recognition technology |
| title_short | Human computer interaction using isolated-words speech recognition technology |
| title_sort | human computer interaction using isolated words speech recognition technology |
| topic | T Technology (General) |
| url | http://irep.iium.edu.my/5881/1/04658569.pdf |
| work_keys_str_mv | AT abushariahmohammadabdalrahmanmahmoud humancomputerinteractionusingisolatedwordsspeechrecognitiontechnology AT ainonrajanoor humancomputerinteractionusingisolatedwordsspeechrecognitiontechnology AT zainuddinroziati humancomputerinteractionusingisolatedwordsspeechrecognitiontechnology AT khalifaothmanomran humancomputerinteractionusingisolatedwordsspeechrecognitiontechnology |