Noise suppression methods for robust speech processing (1 April 1979- 30 Sept. 1979)

Robust speech processing in practical operating environments requires effective environmental and processor noise suppression. This report describes the technical findings and accomplishments during this reporting period for the research program funded 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 the current research and results in the areas of noise suppression using the dual input adaptive noise cancellation using the LMS and gradient lattice algorithms, to spectral analysis and synthesis using the constant -Q trans form, articulation rate change techniques, analytic continuation of band limited signals or signal extrapolation, and two-dimensional automatic gain control.