Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model
This paper investigates on the contribution of Line Spectral Frequency (LSF) derived directly from the G.729 encoded bitstream on Speaker Recognition System over IP network. In this work theGaussian Mixture Model (GMM) are used for the modeling task. The performance of the proposed system is analyze...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Editura Universităţii din Oradea
2013-05-01
|
Series: | Journal of Electrical and Electronics Engineering |
Subjects: | |
Online Access: | https://electroinf.uoradea.ro/images/articles/CERCETARE/Reviste/JEEE/JEEE_V6_N1_MAY_2013/Zergat_may2013.pdf |
_version_ | 1811344433136795648 |
---|---|
author | ZERGAT Kawthar Yasmine AMROUCHE Abderrahmane |
author_facet | ZERGAT Kawthar Yasmine AMROUCHE Abderrahmane |
author_sort | ZERGAT Kawthar Yasmine |
collection | DOAJ |
description | This paper investigates on the contribution of Line Spectral Frequency (LSF) derived directly from the G.729 encoded bitstream on Speaker Recognition System over IP network. In this work theGaussian Mixture Model (GMM) are used for the modeling task. The performance of the proposed system is analyzed from either the synthesized speech and directly from the coded parameters. The effect of the transmission channel is also studied and the channel is simulated using Binary Symmetric Channel (BSC) at different probability values. The recognition phase was tested with ARADIGIT corpus which is a database of Arabic spoken digits, spoken by Algerianspeakers. The obtained results show that the emerging method that uses the LSF derived directly from the G.729 bitstream improves significantly the recognition accuracy compared with the Mel Frequency Cepstral Coefficients (MFCC) features extracted fromsynthesized speech. |
first_indexed | 2024-04-13T19:47:15Z |
format | Article |
id | doaj.art-7dbada42dc4449989e31793589b1f722 |
institution | Directory Open Access Journal |
issn | 1844-6035 2067-2128 |
language | English |
last_indexed | 2024-04-13T19:47:15Z |
publishDate | 2013-05-01 |
publisher | Editura Universităţii din Oradea |
record_format | Article |
series | Journal of Electrical and Electronics Engineering |
spelling | doaj.art-7dbada42dc4449989e31793589b1f7222022-12-22T02:32:41ZengEditura Universităţii din OradeaJournal of Electrical and Electronics Engineering1844-60352067-21282013-05-0161159162Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture ModelZERGAT Kawthar YasmineAMROUCHE AbderrahmaneThis paper investigates on the contribution of Line Spectral Frequency (LSF) derived directly from the G.729 encoded bitstream on Speaker Recognition System over IP network. In this work theGaussian Mixture Model (GMM) are used for the modeling task. The performance of the proposed system is analyzed from either the synthesized speech and directly from the coded parameters. The effect of the transmission channel is also studied and the channel is simulated using Binary Symmetric Channel (BSC) at different probability values. The recognition phase was tested with ARADIGIT corpus which is a database of Arabic spoken digits, spoken by Algerianspeakers. The obtained results show that the emerging method that uses the LSF derived directly from the G.729 bitstream improves significantly the recognition accuracy compared with the Mel Frequency Cepstral Coefficients (MFCC) features extracted fromsynthesized speech.https://electroinf.uoradea.ro/images/articles/CERCETARE/Reviste/JEEE/JEEE_V6_N1_MAY_2013/Zergat_may2013.pdfG.729MFCCLSFGMMBSCSpeaker recognition |
spellingShingle | ZERGAT Kawthar Yasmine AMROUCHE Abderrahmane Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model Journal of Electrical and Electronics Engineering G.729 MFCC LSF GMM BSC Speaker recognition |
title | Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model |
title_full | Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model |
title_fullStr | Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model |
title_full_unstemmed | Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model |
title_short | Influence of G.729 Coded Bitstream in Automatic Speaker Recognition Using Gaussian Mixture Model |
title_sort | influence of g 729 coded bitstream in automatic speaker recognition using gaussian mixture model |
topic | G.729 MFCC LSF GMM BSC Speaker recognition |
url | https://electroinf.uoradea.ro/images/articles/CERCETARE/Reviste/JEEE/JEEE_V6_N1_MAY_2013/Zergat_may2013.pdf |
work_keys_str_mv | AT zergatkawtharyasmine influenceofg729codedbitstreaminautomaticspeakerrecognitionusinggaussianmixturemodel AT amroucheabderrahmane influenceofg729codedbitstreaminautomaticspeakerrecognitionusinggaussianmixturemodel |