Noise Suppression Methods for Robust Speech Processing

Abstract

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1979
Accession Number
ADA068429

Entities

People

  • Ben Cox
  • Craig K. Rushforth
  • Dennis Pulsipher
  • Steven F. Boll
  • William Done

Organizations

  • University of Utah

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Ambient Noise
  • Background Noise
  • Command And Control
  • Computer Science
  • Data Science
  • Detection
  • Detectors
  • Frequency Bands
  • Human Factors Engineering
  • Information Processing
  • Information Science
  • Noise Reduction
  • Recognition
  • Signal Processing
  • Speech Compression
  • Statistics

Fields of Study

  • Engineering

Readers

  • Approximation Theory.
  • Speech Processing/Speech Recognition.

Technology Areas

  • Fully Networked C3
  • Fully Networked C3 - Command and Control