Browse Prior Art Database

Phonetic Labeling of Speech Frames to Help Lip-Reading

IP.com Disclosure Number: IPCOM000113750D
Original Publication Date: 1994-Sep-01
Included in the Prior Art Database: 2005-Mar-27
Document File: 2 page(s) / 58K

Publishing Venue

IBM

Related People

Destombes, F: AUTHOR

Abstract

The device disclosed here allows to produce phonetic symbols to assist deaf persons to lip-read more efficiently. It consists of: 1. A microphone linked to an acoustic component. 2. An acoustic component to determine the frequency spectrum of successive sound "frames" (short duration segments). For example, the technique used to compute such a spectrum might be Linear Predictive Coding. 3. A memory device holding models spectra obtained in a training phase for the stable part of a number of phonemes. 4. A comparison mechanism to find which model spectrum is closest to an incoming unknown spectrum. 5. A visualization mechanism to display phonetic symbols or other shapes representing phonetic symbols. 6. A control mechanism to coordinate the device operation.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 53% of the total text.

Phonetic Labeling of Speech Frames to Help Lip-Reading

      The device disclosed here allows to produce phonetic symbols to
assist deaf persons to lip-read more efficiently.  It consists of:
  1.  A microphone linked to an acoustic component.
  2.  An acoustic component to determine the frequency spectrum of
      successive sound "frames" (short duration segments).   For
      example, the technique used to compute such  a spectrum might
be
      Linear Predictive Coding.
  3.  A memory device holding models spectra obtained in a training
      phase for the stable part of a number of phonemes.
  4.  A comparison mechanism to find which model spectrum is closest
to
      an incoming unknown spectrum.
  5.  A visualization mechanism to display phonetic symbols or other
      shapes representing phonetic symbols.
  6.  A control mechanism to coordinate the device operation.

Under control of the control mechanism, the following operations are
performed:
  o  Speech sounds are captured by the microphone.  The acoustic
     component computes spectra for successive frames (short duration
     segments).
  o  The comparison mechanism searches the model spectra, computing a
     distance between each model and the spectrum of an incoming
     frame.  The label of the model yielding the smallest distance is
     attached to the incoming frame.
  o  The control mechanism gathers successive frame labels and takes
     decisions to produce and visualize phonetic symbols.  Such
     decisions a...