Title :
Non-parametric estimation and correction of non-linear distortion in speech systems
Author :
Balchandran, Rajesh ; Mammone, Richard J.
Author_Institution :
CAIP Center, Rutgers Univ., Piscataway, NJ, USA
Abstract :
The performance of speech systems such as speaker recognition degrades drastically when there is mismatch between training and testing conditions, caused by non-linear distortion. This paper describes a technique to estimate and correct such non-linear distortion in speech. The focus is on constrained restoration of degraded speech, that is distortion in the test speech is undone relative to the training speech. Restoration is a two step process-estimation followed by inversion. The non-linearity is estimated in the form of a look-up table by a process of statistical matching using a reference speech template. This statistical matching technique provides a very good estimate of the true non-linear characteristic, and the process is robust, computationally efficient, and universally applicable. Speaker-ID experiments, using artificially corrupted test speech, showed significant improvement in performance after the test speech was `cleaned´ using this technique. The restoration process itself does not introduce appreciable distortion
Keywords :
estimation theory; nonparametric statistics; speaker recognition; table lookup; artificially corrupted test speech; constrained restoration; inversion process; look-up table; nonlinear distortion correction; nonparametric estimation; reference speech template; speaker recognition; speech restoration; speech systems; statistical matching; test speech; training speech; Filtering; Nonlinear distortion; Random variables; Speech processing; Table lookup; Testing; Training data;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.675373