Combining evidence from residual phase and MFCC features for speaker recognition
Authors:
Top Cited Papers
- 19 December 2005
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 13 (1) , 52-55
Abstract
The objective of this letter is to demonstrate the complementary nature of speaker-specific information present in the residual phase in comparison with the information present in the conventional mel-frequency cepstral coefficients (MFCCs). The residual phase is derived from speech signal by linear prediction analysis. Speaker recognition studies are conducted on the NIST-2003 database using the proposed residual phase and the existing MFCC features. The speaker recognition system based on the residual phase gives an equal error rate (EER) of 22%, and the system using the MFCC features gives an EER of 14%. By combining the evidence from both the residual phase and the MFCC features, an EER of 10.5% is obtained, indicating that speaker-specific excitation information is present in the residual phase. This information is useful since it is complementary to that of MFCCs.Keywords
This publication has 12 references indexed in Scilit:
- Speaker-specific information from residual phase2005
- Analysis of autoassociative mapping neural networks2003
- Online text-independent speaker verification system using autoassociative neural network models2002
- Source and system features for speaker recognition using AANN models2002
- AANN: an alternative to GMM for pattern recognitionNeural Networks, 2002
- Score Normalization for Text-Independent Speaker Verification SystemsDigital Signal Processing, 2000
- Modeling of the glottal flow derivative waveform with application to speaker identificationIEEE Transactions on Speech and Audio Processing, 1999
- Speaker recognitionIEEE ASSP Magazine, 1986
- Cepstral analysis technique for automatic speaker verificationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Epoch extraction from linear prediction residual for identification of closed glottis intervalIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979