Analysis of Feature Extraction and Channel Compensation in a GMM Speaker Recognition System
- 1 September 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 15 (7) , 1979-1986
Abstract
In this paper, several feature extraction and channel compensation techniques found in state-of-the-art speaker verification systems are analyzed and discussed. For the NIST SRE 2006 submission, cepstral mean subtraction, feature warping, RelAtive SpecTrAl (RASTA) filtering, heteroscedastic linear discriminant analysis (HLDA), feature mapping, and eigenchannel adaptation were incrementally added to minimize the system's error rate. This paper deals with eigenchannel adaptation in more detail and includes its theoretical background and implementation issues. The key part of the paper is, however, the post-evaluation analysis, undermining a common myth that ldquothe more boxes in the scheme, the better the system.rdquo All results are presented on NIST Speaker Recognition Evaluation (SRE) 2005 and 2006 data.Keywords
This publication has 12 references indexed in Scilit:
- Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006IEEE Transactions on Audio, Speech, and Language Processing, 2007
- STBU System for the NIST 2006 Speaker Recognition Evaluation2007
- Advances In Channel Compensation For SVM Speaker Recognition2006
- Hierarchical Structures of Neural Networks for Phoneme Recognition2006
- Experiments in Session Variability Modelling for Speaker Verification2006
- Disentangling speaker and channel effects in speaker verification2004
- Channel robust speaker verification via feature mapping2003
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000
- Score Normalization for Text-Independent Speaker Verification SystemsDigital Signal Processing, 2000
- Semi-tied covariance matrices for hidden Markov modelsIEEE Transactions on Speech and Audio Processing, 1999