Combining Evidences from Mel Cepstral Features and Cepstral Mean Subtracted Features for Singer Identification
Authors:
- Hemant A. PatilHPHemant A. Patil
- Purushotam G. RadadiaPRPurushotam G. Radadia
- T.K. BasuTBT.K. Basu
- 1 November 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 145-148
Abstract
One of the challenging and difficult problems under the category of Music Information Retrieval (MIR) is to identify a singer of a given song under the strong influence of instrumental sounds. The performance of Singer Identification (SID) system is also severely affected by the quality of recording devices, transmission channels and singing voice(s) of other singer(s). We have proposed a large database of 500 songs, prepared from Hindi Bollywood songs. The State-of-the-art Mel Frequency Cepstral Coefficients (MFCC) are used as feature vectors and 2nd order polynomial classifier is employed as a pattern classifier in our work. We also used Cepstral Mean Subtraction (CMS) based MFCC (CMSMFCC) feature vectors for SID and are found to give better results than the MFCC on proposed database. The SID accuracy for MFCC and CMSMFCC was found to be 75.75% and 84.5%, respectively and Equal Error Rate (EER) for MFCC and CMSMFCC was found to be 9.48% and 8.45%, respectively. While score-level-fusion of both gave improvement in SID accuracy and EER by 10.25% and 2.08% respectively than MFCC alone.Keywords
This publication has 8 references indexed in Scilit:
- Singer Identification Using Time-Frequency Audio Feature2011
- Exploring Vibrato-Motivated Acoustic Features for Singer IdentificationIEEE Transactions on Audio, Speech, and Language Processing, 2007
- Automatic singer recognition of popular music recordings via estimation and modeling of solo vocal signalsIEEE Transactions on Audio, Speech, and Language Processing, 2005
- Singing Voice Identification Using Spectral Envelope EstimationIEEE Transactions on Speech and Audio Processing, 2004
- Artist detection in music with Minnowmatch2002
- Speaker recognition with polynomial classifiersIEEE Transactions on Speech and Audio Processing, 2002
- The DET curve in assessment of detection task performance1997
- Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verificationThe Journal of the Acoustical Society of America, 1974