Title :
Improving SVM-based speech/music classifier based on conditional MAP criterion
Author :
Lim, Chungsoo ; Chang, Joon-Hyuk ; Lee, Seong-Ro
Author_Institution :
Mokpo Nat. Univ., Mokpo, South Korea
Abstract :
To enhance SVM-based speech/music classifications by exploiting substantial inter-frame correlations in speech/music frames, we propose a technique using the second-order conditional maximum a posteriori (CMAP) probability that considers not only the current observation but also the classification results of the two previous frames.
Keywords :
correlation methods; maximum likelihood estimation; music; probability; signal classification; speech processing; support vector machines; CMAP probability; SVM-based speech/music classifier; conditional MAP criterion; interframe correlation; second-order conditional maximum a posteriori; Codecs; Correlation; Electronic mail; Speech; Speech enhancement; Support vector machines; Training;
Conference_Titel :
ICT Convergence (ICTC), 2011 International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4577-1267-8
DOI :
10.1109/ICTC.2011.6082609
