Pronunciation learning for automatic speech recognition
Name
751988889-MIT.pdf
Description
Full printable version
Size
6.73 MB
Format
Adobe PDF
Checksum (MD5)
719a902de8faf5774da1ea7485586bca
Author(s)
Badr, Ibrahim
Advisor(s)
James Glass.
Alternative Title
Learning pronunciation for automatic speech recognition
Date Issued
2011
Publisher
Massachusetts Institute of Technology
Abstract
In many ways, the lexicon remains the Achilles heel of modern automatic speech recognizers (ASRs). Unlike stochastic acoustic and language models that learn the values of their parameters from training data, the baseform pronunciations of words in an ASR vocabulary are typically specified manually, and do not change, unless they are edited by an expert. Our work presents a novel generative framework that uses speech data to learn stochastic lexicons, thereby taking a step towards alleviating the need for manual intervention and automnatically learning high-quality baseform pronunciations for words. We test our model on a variety of domains: an isolated-word telephone speech corpus, a weather query corpus and an academic lecture corpus. We show significant improvements of 25%, 15% and 2% over expert-pronunciation lexicons, respectively. We also show that further improvements can be made by combining our pronunciation learning framework with acoustic model training.
Description
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 99-101).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
Persistent DSpace Link
