ResearchSpace

Automatic speaker recognition system based on optimised machine learning algorithms

Show simple item record

dc.contributor.author Mokgonyane, TB
dc.contributor.author Sefara, Tshephisho J
dc.contributor.author Modipa, TI
dc.contributor.author Manamela, MJ
dc.date.accessioned 2020-10-05T08:59:58Z
dc.date.available 2020-10-05T08:59:58Z
dc.date.issued 2019-09
dc.identifier.citation Mokgonyane, T.B. (et.al.) 2019. Automatic speaker recognition system based on optimised machine learning algorithms. IEEE AFRICON, Accra, Ghana, 25-27 September 2019, 7pp. en_US
dc.identifier.isbn 978-1-7281-3289-1
dc.identifier.uri https://dblp.org/db/conf/africon/index.html
dc.identifier.uri africon2019.org
dc.identifier.uri https://ieeexplore.ieee.org/document/9133823
dc.identifier.uri DOI: 10.1109/AFRICON46755.2019.9133823
dc.identifier.uri http://hdl.handle.net/10204/11592
dc.description Copyright: 2019 IEEE. This is the accepted version of the published item. en_US
dc.description.abstract Speaker recognition is a technique that automatically identifies a speaker from a recording of their voice. Speaker recognition technologies are taking a new trend due to the progress in artificial intelligence and machine learning and have been widely used in many domains. Continuing research in the field of speaker recognition has now spanned over 50 years. In over half a century, a great deal of progress has been made towards improving the accuracy of the system’s decisions, through the use of more successful machine learning algorithms. This paper presents the development of automatic speaker recognition system based on optimised machine learning algorithms. The algorithms are optimised for better and improved performance. Four classifier models, namely, Support Vector Machines, K-Nearest Neighbors, Random Forest, Logistic Regression, and Artificial Neural Networks are trained and compared. The system resulted with Artificial Neural Networks obtaining the state-ofthe-art accuracy of 96.03% outperforming KNN, SVM, RF and LR classifiers. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.relation.ispartofseries Worklist;23676
dc.subject Speaker recognition en_US
dc.subject Support vector machines en_US
dc.subject K-nearest neighbors en_US
dc.subject Artificial neural networks en_US
dc.subject Logistic regression en_US
dc.title Automatic speaker recognition system based on optimised machine learning algorithms en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Mokgonyane, T., Sefara, T. J., Modipa, T., & Manamela, M. (2019). Automatic speaker recognition system based on optimised machine learning algorithms. IEEE. http://hdl.handle.net/10204/11592 en_ZA
dc.identifier.chicagocitation Mokgonyane, TB, Tshephisho J Sefara, TI Modipa, and MJ Manamela. "Automatic speaker recognition system based on optimised machine learning algorithms." (2019): http://hdl.handle.net/10204/11592 en_ZA
dc.identifier.vancouvercitation Mokgonyane T, Sefara TJ, Modipa T, Manamela M, Automatic speaker recognition system based on optimised machine learning algorithms; IEEE; 2019. http://hdl.handle.net/10204/11592 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Mokgonyane, TB AU - Sefara, Tshephisho J AU - Modipa, TI AU - Manamela, MJ AB - Speaker recognition is a technique that automatically identifies a speaker from a recording of their voice. Speaker recognition technologies are taking a new trend due to the progress in artificial intelligence and machine learning and have been widely used in many domains. Continuing research in the field of speaker recognition has now spanned over 50 years. In over half a century, a great deal of progress has been made towards improving the accuracy of the system’s decisions, through the use of more successful machine learning algorithms. This paper presents the development of automatic speaker recognition system based on optimised machine learning algorithms. The algorithms are optimised for better and improved performance. Four classifier models, namely, Support Vector Machines, K-Nearest Neighbors, Random Forest, Logistic Regression, and Artificial Neural Networks are trained and compared. The system resulted with Artificial Neural Networks obtaining the state-ofthe-art accuracy of 96.03% outperforming KNN, SVM, RF and LR classifiers. DA - 2019-09 DB - ResearchSpace DP - CSIR KW - Speaker recognition KW - Support vector machines KW - K-nearest neighbors KW - Artificial neural networks KW - Logistic regression LK - https://researchspace.csir.co.za PY - 2019 SM - 978-1-7281-3289-1 T1 - Automatic speaker recognition system based on optimised machine learning algorithms TI - Automatic speaker recognition system based on optimised machine learning algorithms UR - http://hdl.handle.net/10204/11592 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record