Accession Number:

ADA350494

Title:

Improving Acoustic Models by Watching Television

Descriptive Note:

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE

Report Date:

1998-03-19

Pagination or Media Count:

6.0

Abstract:

Obtaining sufficient labelled training data is a persistent difficulty for speech recognition research. Although well transcribed data is expensive to produce, there is a constant stream of challenging speech data and poor transcription broadcast as closed-captioned television. We describe a reliable unsupervised method for identifying accurately transcribed sections of these broadcasts, and show how these segments can be used to train a recognition system. Starting from acoustic models trained on the Wall Street Journal database, a single iteration of our training method reduced the word error rate on an independent broadcast television news test set from 62.2 to 59.5.

Subject Categories:

  • Cybernetics
  • Voice Communications
  • Linguistics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE