Noise Suppression Methods for Robust Speech Processing

Robust speech processing in practical operating environments requires effective environmental and processor noise suppression. This report describes the technical findings and accomplishments to develop real time, compressed speech analysis-synthesis algorithms whose performance is invariant under signal contamination. Fulfillment of this requirement is necessary to insure reliable secure compressed speech transmission within realistic military command and control environments. Overall contributions resulting from this research program include the understanding of how environmental noise degrades narrow band, coded speech, development of appropriate real time noise suppression algorithms, and development of speech parameter identification methods that consider signal contamination as a fundamental element in the estimation process. This report describes results in the areas of noise suppression using the spectral subtraction algorithm, dual input adaptive noise cancellation using the LMS algorithm, pole-zero parameter estimation, nonparametric-rank order statistics with applications to Robust Speech Activity detection, spectral analysis and synthesis using the constant-Q transform, and pitch and rate changes to speech using the constant-Q transform. Sponsored in part by DARPA.