A 3-level endpoint detection algorithm for isolated speech and frequency-based features
This paper proposed a new approach for endpoint detection of isolated speech, which proves to significantly improve the endpoint detection performance. The proposed algorithm relies on the root mean square energy (rms energy), zero crossing rate and spectral characteristics of the speech signal wher...
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/20757/1/GohKiaEng2004_A3LevelEndpointDetectionAlgorithm.pdf |
| _version_ | 1796855843499540480 |
|---|---|
| author | Goh, K. E. Ahmad, A. M. |
| author_facet | Goh, K. E. Ahmad, A. M. |
| author_sort | Goh, K. E. |
| collection | ePrints |
| description | This paper proposed a new approach for endpoint detection of isolated speech, which proves to significantly improve the endpoint detection performance. The proposed algorithm relies on the root mean square energy (rms energy), zero crossing rate and spectral characteristics of the speech signal where the Euclidean distance measure is adopted using cepstral coefficients to accurately detect the endpoint of isolated speech. The algorithm offers better performance than traditional energy-based algorithm. The vocabulary for the experiment includes English digit from one to nine. These experimental results were conducted by 360 utterances from a male speaker. Experimental results show that the accuracy of the algorithm is quite acceptable. Moreover, the computation overload of this algorithm is low since the cepstral coefficients parameters will be used in feature extraction later of speech recognition procedure. |
| first_indexed | 2024-03-05T18:34:33Z |
| format | Conference or Workshop Item |
| id | utm.eprints-20757 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T18:34:33Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | utm.eprints-207572022-02-28T12:18:26Z http://eprints.utm.my/20757/ A 3-level endpoint detection algorithm for isolated speech and frequency-based features Goh, K. E. Ahmad, A. M. QA75 Electronic computers. Computer science This paper proposed a new approach for endpoint detection of isolated speech, which proves to significantly improve the endpoint detection performance. The proposed algorithm relies on the root mean square energy (rms energy), zero crossing rate and spectral characteristics of the speech signal where the Euclidean distance measure is adopted using cepstral coefficients to accurately detect the endpoint of isolated speech. The algorithm offers better performance than traditional energy-based algorithm. The vocabulary for the experiment includes English digit from one to nine. These experimental results were conducted by 360 utterances from a male speaker. Experimental results show that the accuracy of the algorithm is quite acceptable. Moreover, the computation overload of this algorithm is low since the cepstral coefficients parameters will be used in feature extraction later of speech recognition procedure. 2004 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/20757/1/GohKiaEng2004_A3LevelEndpointDetectionAlgorithm.pdf Goh, K. E. and Ahmad, A. M. (2004) A 3-level endpoint detection algorithm for isolated speech and frequency-based features. In: International conference on Control, Automation And system, 2004, The Shangri-La Hotel, Bangkok, Thailand. https://scienceon.kisti.re.kr/srch/selectPORSrchArticle.do?cn=NPAP08127118&SITE |
| spellingShingle | QA75 Electronic computers. Computer science Goh, K. E. Ahmad, A. M. A 3-level endpoint detection algorithm for isolated speech and frequency-based features |
| title | A 3-level endpoint detection algorithm for isolated speech and frequency-based features |
| title_full | A 3-level endpoint detection algorithm for isolated speech and frequency-based features |
| title_fullStr | A 3-level endpoint detection algorithm for isolated speech and frequency-based features |
| title_full_unstemmed | A 3-level endpoint detection algorithm for isolated speech and frequency-based features |
| title_short | A 3-level endpoint detection algorithm for isolated speech and frequency-based features |
| title_sort | 3 level endpoint detection algorithm for isolated speech and frequency based features |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.utm.my/20757/1/GohKiaEng2004_A3LevelEndpointDetectionAlgorithm.pdf |
| work_keys_str_mv | AT gohke a3levelendpointdetectionalgorithmforisolatedspeechandfrequencybasedfeatures AT ahmadam a3levelendpointdetectionalgorithmforisolatedspeechandfrequencybasedfeatures AT gohke 3levelendpointdetectionalgorithmforisolatedspeechandfrequencybasedfeatures AT ahmadam 3levelendpointdetectionalgorithmforisolatedspeechandfrequencybasedfeatures |