Noise Suppression Methods for Robust Speech Processing

Abstract

A stand alone noise suppression algorithm is presented for reducing the spectral effects of acoustically added noise in speech. Effective performance of digital speech processors operating in practical environments may require suppression of noise from the digital waveform. Spectral subtraction offers a computationally efficient, processor independent, approach to effective digital speech analysis. The method, requiring about the same computation as high-speed convolution, suppresses stationary noise for speech by subtracting the spectral noise bias calculated during non-speech activity. Secondary procedures and then applied to attenuate the residual noise left after subtraction. Since the algorithm resynthesizes a speech waveform, it can be used as a preprocessor to narrow band voice communications systems, speech recognition systems or speaker authentication systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1978
Accession Number
ADA064694

Entities

People

  • B. V. Cox
  • Dennis Pulsipher
  • L. K. Timothy
  • Steven F. Boll
  • William Done

Organizations

  • University of Utah

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Communication Systems
  • Data Science
  • Databases
  • Detection
  • Detectors
  • Electrical Engineering
  • Filters
  • Frequency Bands
  • Helicopters
  • Information Processing
  • Information Science
  • Order Statistics
  • Pattern Recognition
  • Probability
  • Speech Analysis
  • Speech Compression
  • Statistics

Readers

  • Approximation Theory.
  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference