Covariance estimation methods for channel robust text-independent speaker identification
- Resource Type
- Conference
- Authors
- Schmidt, M.; Gish, H.; Mielke, A.
- Source
- 1995 International Conference on Acoustics, Speech, and Signal Processing Acoustics, speech and signal processing Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on. 1:333-336 vol.1 1995
- Subject
- Signal Processing and Analysis
Components, Circuits, Devices and Systems
Testing
Additive noise
Covariance matrix
Statistical distributions
Noise robustness
Error analysis
Shape
Cepstral analysis
Speech
Probability
- Language
- ISSN
- 1520-6149
Two novel channel robust methods are described for performing text-independent speaker identification. The first technique models speaker's voices stochastically via cepstra correlations rather than by covariances in an effort to compensate for additive noise. The second technique, which we term dynamic covariances, models speakers by covariances of deviations of cepstra from time varying means rather than from constant means. Dynamic covariances may normalize for time varying channel effects, utterance lengths and text. Experimental results are obtained on the SPIDRE subset of the Switchboard corpus. Error rates as low as 2.2% are obtained using the new models.