2026-09-18T21:43:20Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/660222022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
James Glass.
Badr, Ibrahim
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2011-09-27T18:33:33Z
2011-09-27T18:33:33Z
2011
2011
http://hdl.handle.net/1721.1/66022
751988889
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).
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.
by Ibrahim Badr.
S.M.
101 p.
eng
Massachusetts Institute of Technology
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.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Pronunciation learning for automatic speech recognition
Learning pronunciation for automatic speech recognition
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d4d1925c-7bb2-416c-9e00-a6445bc04fdb">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Pronunciation learning for automatic speech recognition</Title>
<Subtitle>Learning pronunciation for automatic speech recognition</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2011</PublicationDate>
<Authors>
<Author>
<DisplayName>Badr, Ibrahim</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>