Speaker recognition using adaptively boosted decision tree classifier
In this paper, a novel approach for speaker recognition is proposed. The approach makes use of adaptive boosting (AdaBoost) and C4.5 decision trees for closed set, text-dependent speaker recognition. A subset of 20 speakers, 10 male and 10 female, drawn from the YOHO speaker verification corpus is...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2009
|
| Online Access: | https://hdl.handle.net/10356/79870 http://hdl.handle.net/10220/4615 |
| _version_ | 1826115270980141056 |
|---|---|
| author | Foo, Say Wei Lim, Eng Guan |
| author2 | IEEE International Conference on Acoustics, Speech and Signal Processing (2002 : Orlando, Florida, US) |
| author_facet | IEEE International Conference on Acoustics, Speech and Signal Processing (2002 : Orlando, Florida, US) Foo, Say Wei Lim, Eng Guan |
| author_sort | Foo, Say Wei |
| collection | NTU |
| description | In this paper, a novel approach for speaker
recognition is proposed. The approach makes use of adaptive boosting (AdaBoost) and C4.5 decision trees for closed set, text-dependent speaker recognition. A subset
of 20 speakers, 10 male and 10 female, drawn from the YOHO speaker verification corpus is used to assess the performance of the system. Results reveal that an accuracy of 99.5% of speaker identification may be
achieved. |
| first_indexed | 2024-10-01T03:52:26Z |
| format | Conference Paper |
| id | ntu-10356/79870 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:52:26Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | ntu-10356/798702019-12-06T13:35:46Z Speaker recognition using adaptively boosted decision tree classifier Foo, Say Wei Lim, Eng Guan IEEE International Conference on Acoustics, Speech and Signal Processing (2002 : Orlando, Florida, US) In this paper, a novel approach for speaker recognition is proposed. The approach makes use of adaptive boosting (AdaBoost) and C4.5 decision trees for closed set, text-dependent speaker recognition. A subset of 20 speakers, 10 male and 10 female, drawn from the YOHO speaker verification corpus is used to assess the performance of the system. Results reveal that an accuracy of 99.5% of speaker identification may be achieved. Published version 2009-05-25T03:17:31Z 2019-12-06T13:35:46Z 2009-05-25T03:17:31Z 2019-12-06T13:35:46Z 2002 2002 Conference Paper Foo, S. W., & Lim, E. G. (2002). Speaker recognition using adaptively boosted decision tree classifier. IEEE International Conference on Acoustics, Speech and Signal Processing 2002. (pp. 157-160). https://hdl.handle.net/10356/79870 http://hdl.handle.net/10220/4615 en IEEE International Conference on Acoustics, Speech and Signal Processing. Journal can be found at http://ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=7874 4 p. application/pdf |
| spellingShingle | Foo, Say Wei Lim, Eng Guan Speaker recognition using adaptively boosted decision tree classifier |
| title | Speaker recognition using adaptively boosted decision tree classifier |
| title_full | Speaker recognition using adaptively boosted decision tree classifier |
| title_fullStr | Speaker recognition using adaptively boosted decision tree classifier |
| title_full_unstemmed | Speaker recognition using adaptively boosted decision tree classifier |
| title_short | Speaker recognition using adaptively boosted decision tree classifier |
| title_sort | speaker recognition using adaptively boosted decision tree classifier |
| url | https://hdl.handle.net/10356/79870 http://hdl.handle.net/10220/4615 |
| work_keys_str_mv | AT foosaywei speakerrecognitionusingadaptivelyboosteddecisiontreeclassifier AT limengguan speakerrecognitionusingadaptivelyboosteddecisiontreeclassifier |