Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Feature extraction and normalization in SVM speaker verification using telephone speech
Includes bibliographical references (leaves 105-116).
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Electrical Engineering
2014
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613320261926912 |
|---|---|
| access_status_str | Open Access |
| author | Mazibuko, Thembisile Thulisile |
| author_browse | Mazibuko, Thembisile Thulisile |
| author_facet | Mazibuko, Thembisile Thulisile |
| author_sort | Mazibuko, Thembisile Thulisile |
| collection | Thesis |
| description | Includes bibliographical references (leaves 105-116). |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/5167 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:34:14.045Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2014 |
| publishDateRange | 2014 |
| publishDateSort | 2014 |
| publisher | Department of Electrical Engineering |
| publisherStr | Department of Electrical Engineering |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/5167 Feature extraction and normalization in SVM speaker verification using telephone speech Mazibuko, Thembisile Thulisile Electrical Engineering Includes bibliographical references (leaves 105-116). In this research the Support Vector Machine classifier is applied to a text independent speaker verification task using conversational telephone speech from the NIST 2000 Speaker Recognition Evaluation. The SVM is a discriminative classifier with good generalization characteristics. It has been shown to perform as well as, and sometimes outperform the more widely used Gaussian Mixture Model. The SVM, like other classifiers is vulnerable to environmental noise, distortions from transmission over communication channels such as the telephone channel, and intersession variability. 2014-07-31T10:54:50Z 2014-07-31T10:54:50Z 2007 Master Thesis Masters MSc http://hdl.handle.net/11427/5167 eng application/pdf Department of Electrical Engineering Faculty of Engineering and the Built Environment University of Cape Town |
| spellingShingle | Electrical Engineering Mazibuko, Thembisile Thulisile Feature extraction and normalization in SVM speaker verification using telephone speech |
| thesis_degree_str | Master's |
| title | Feature extraction and normalization in SVM speaker verification using telephone speech |
| title_full | Feature extraction and normalization in SVM speaker verification using telephone speech |
| title_fullStr | Feature extraction and normalization in SVM speaker verification using telephone speech |
| title_full_unstemmed | Feature extraction and normalization in SVM speaker verification using telephone speech |
| title_short | Feature extraction and normalization in SVM speaker verification using telephone speech |
| title_sort | feature extraction and normalization in svm speaker verification using telephone speech |
| topic | Electrical Engineering |
| url | http://hdl.handle.net/11427/5167 |
| work_keys_str_mv | AT mazibukothembisilethulisile featureextractionandnormalizationinsvmspeakerverificationusingtelephonespeech |