Speech Recognition Using Visible and Infrared Detectors

Abstract

A system has been developed that tracks lip motion using infrared (IR) or visible detectors. Tne purpose of this study was to determine if the additional information obtained from the IR or visible detectors can be used to increase the recognition rate of audio Automatic Speech Recognition (ASR) systems. To accomplish this goal, several hardware analog prototypes had to be designed, built and tested. Different detectors (IR and visible) and modes of operation (active and passive) were tried before a reliable and useful signal was found. An analog-to-digital (A/D) board was then designed and built that digitized both the microphone and photo signals. Software algorithms, executed from a desktop PC, were used to interface with the A/D board, process the digitized data, and perform certain optical and audio ASR experiments. The results showed that isolated ASR audio recognition rates increased after using additional information gained from the photo speech signals. However, the results for the continuous case were inconclusive since not all of the available photo information was utilized to perform ASR experiments.... Speech recognition, IR, Visible, Detectors, Audio, DTW, Photo, Sensors, ASR, A/D.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1992
Accession Number
ADA262490

Entities

People

  • Patrick T. Marshall

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Acquisition
  • Air Force
  • Aircrafts
  • Algorithms
  • Automated Speech Recognition
  • Computer Programming
  • Computer Programs
  • Computers
  • Data Acquisition
  • Detection
  • Detectors
  • Electrical Engineering
  • Infrared Detectors
  • Microphones
  • Recognition
  • Signal Processing
  • Word Recognition

Readers

  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Spectroscopy.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML