Analysis and Improvement of Speech/Music Classification for 3GPP2 SMV Based on GMM

In this letter, a novel approach is proposed to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the Gaussian mixture model (GMM). An in-depth analysis of the features and classification method adopted in the conventional SMV is performed. F...

Full description

Saved in:
Bibliographic Details
Published inIEEE signal processing letters Vol. 15; pp. 103 - 106
Main Authors Song, Ji-Hyun, Lee, Kye-Hwan, Chang, Joon-Hyuk, Kim, Jong Kyu, Kim, Nam Soo
Format Journal Article
LanguageEnglish
Published New York IEEE 2008
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Adaptive filters
Bandwidth
Counting circuits
Gaussian mixture model (GMM)
Linear predictive coding
Multiple signal classification
Performance analysis
selectable mode vocoder (SMV)
Signal processing algorithms
Speech analysis
Speech codecs
speech/music classification
Vocoders
Online AccessGet full text

Cover

More Information
Summary:In this letter, a novel approach is proposed to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the Gaussian mixture model (GMM). An in-depth analysis of the features and classification method adopted in the conventional SMV is performed. Feature vectors applied to the GMM are then selected from the relevant parameters of the SMV for efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme implemented in the SMV.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2007.911184