Accession Number:

ADA460569

Title:

Tied Mixtures in the Lincoln Robust CSR

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB

Personal Author(s):

Report Date:

1989-01-01

Pagination or Media Count:

11.0

Abstract:

HMM recognizers using either a single Gaussian or a Gaussian mixture per state have been shown to work fairly well for 1000-word vocabulary continuous speech recognition. However, the large number of Gaussians required to cover the entire English language makes these systems unwieldy for large vocabulary tasks. Tied mixtures offer a more compact way of representing the observation pdfs. We have converted our independent mixture systems to tied mixtures and have obtained mixed results a 13 improvement in speaker-dependent recognition without cross-word triphone models, but no improvement in our speaker-dependent system with cross-word boundary triphone models or in our speaker-independent system. There is also a reduction in CPU requirements during recognition--but this is counter-balanced by an increase during training. This paper also includes a comment on the validity of the DARPA programs evaluation test system comparisons.

Subject Categories:

  • Voice Communications

Distribution Statement:

APPROVED FOR PUBLIC RELEASE