Robust speaker gender identification using empirical mode decomposition-based cepstral features
Automatic speaker gender identification is a field of research with numerous practical applications. However, this issue has not gained its deserved attention, in particular in the presence of environmental noises. In this paper, using the empirical mode decomposition (EMD), some new and improved me...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2018
|
| Online Access: | http://journalarticle.ukm.my/17756/ http://journalarticle.ukm.my/17756/1/06.pdf |
| _version_ | 1848814392456511488 |
|---|---|
| author | Alipoor, Ghasem Samadi, Ehsan |
| author_facet | Alipoor, Ghasem Samadi, Ehsan |
| author_sort | Alipoor, Ghasem |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | Automatic speaker gender identification is a field of research with numerous practical applications. However, this issue has not gained its deserved attention, in particular in the presence of environmental noises. In this paper, using the empirical mode decomposition (EMD), some new and improved mel-frequency cepstral coefficient (MFCC) features are developed to address the problem of robust speaker gender identification. In the proposed approach, EMD is employed as a filter bank to decompose the speech signal into its frequency bands. Furthermore, another variant is also developed in which the complete ensemble EMD (CEEMD) supersedes the EMD. Moreover, support vector machine (SVM) with radial basis function (RBF) kernel is employed for classification. Performance of these methods is examined for gender identification, in noise-free environments as well as in the presence of various Gaussian and non-Gaussian noises. Simulation results show that, although with fewer features used, utilizing the improved EMD-based cepstral features in noiseless situations leads to the same accuracy as that of the original MFCCs. However, in noisy environments the proposed methods outperform the conventional way of extracting the MFCCs. |
| first_indexed | 2025-11-15T00:33:21Z |
| format | Article |
| id | oai:generic.eprints.org:17756 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T00:33:21Z |
| publishDate | 2018 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:177562021-12-24T08:36:47Z http://journalarticle.ukm.my/17756/ Robust speaker gender identification using empirical mode decomposition-based cepstral features Alipoor, Ghasem Samadi, Ehsan Automatic speaker gender identification is a field of research with numerous practical applications. However, this issue has not gained its deserved attention, in particular in the presence of environmental noises. In this paper, using the empirical mode decomposition (EMD), some new and improved mel-frequency cepstral coefficient (MFCC) features are developed to address the problem of robust speaker gender identification. In the proposed approach, EMD is employed as a filter bank to decompose the speech signal into its frequency bands. Furthermore, another variant is also developed in which the complete ensemble EMD (CEEMD) supersedes the EMD. Moreover, support vector machine (SVM) with radial basis function (RBF) kernel is employed for classification. Performance of these methods is examined for gender identification, in noise-free environments as well as in the presence of various Gaussian and non-Gaussian noises. Simulation results show that, although with fewer features used, utilizing the improved EMD-based cepstral features in noiseless situations leads to the same accuracy as that of the original MFCCs. However, in noisy environments the proposed methods outperform the conventional way of extracting the MFCCs. Penerbit Universiti Kebangsaan Malaysia 2018-06 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/17756/1/06.pdf Alipoor, Ghasem and Samadi, Ehsan (2018) Robust speaker gender identification using empirical mode decomposition-based cepstral features. Asia-Pacific Journal of Information Technology and Multimedia, 7 (1). pp. 71-81. ISSN 2289-2192 https://www.ukm.my/apjitm/articles-year.php |
| spellingShingle | Alipoor, Ghasem Samadi, Ehsan Robust speaker gender identification using empirical mode decomposition-based cepstral features |
| title | Robust speaker gender identification using empirical mode decomposition-based cepstral features |
| title_full | Robust speaker gender identification using empirical mode decomposition-based cepstral features |
| title_fullStr | Robust speaker gender identification using empirical mode decomposition-based cepstral features |
| title_full_unstemmed | Robust speaker gender identification using empirical mode decomposition-based cepstral features |
| title_short | Robust speaker gender identification using empirical mode decomposition-based cepstral features |
| title_sort | robust speaker gender identification using empirical mode decomposition-based cepstral features |
| url | http://journalarticle.ukm.my/17756/ http://journalarticle.ukm.my/17756/ http://journalarticle.ukm.my/17756/1/06.pdf |