Noise-Immune Multisensor Transduction of Speech.

Abstract

Two types of configurations of multiple sensors were developed, tested and evaluated in speech recognition application for robust performance in high levels of acoustic background noise: One type combines the individual sensor signals to provide a single speech signal input, and the other provides several parallel inputs. For single-input systems, several configurations of multiple sensors were developed and tested. Results from formal speech intelligibility and quality tests in simulated fighter aircraft cockpit noise show that each of the two-sensor configurations tested outperforms the constituent individual sensors in high noise. Also presented are results comparing the performance of two-sensor configurations and individual sensors in speaker-dependent, isolated-word speech recognition tests performed using a commercial recognizer (Verbex 4000) in simulated fighter aircraft cockpit noise. Keywords include: Multisensor transduction, Noise Reduction, Speech Enhancement, and Speech Recognition Testing, in Noise.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1986
Accession Number
ADA174693

Entities

People

  • Alan Derr
  • Claudia M. Henry
  • Richard M. Schwartz
  • Salim Roucos
  • Vishu R. Viswanathan

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Aircrafts
  • Algorithms
  • Ambient Noise
  • Artificial Intelligence
  • Background Noise
  • Computational Science
  • Databases
  • Detectors
  • Feature Extraction
  • Fighter Aircraft
  • Hidden Markov Models
  • Human Factors Engineering
  • Intelligibility
  • Language
  • Recognition
  • Word Recognition

Fields of Study

  • Engineering

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Optical Fiber Sensing and Electromagnetic Propagation.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML