2026-09-18T22:20:12Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/531142022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
James R. Glass and I. Lee Hetherington.
Wang, Stanley Xinlei
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2010-03-25T15:02:56Z
2010-03-25T15:02:56Z
2009
2009
http://hdl.handle.net/1721.1/53114
503114771
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.
Includes bibliographical references (p. 87-90).
This research explores applications of joint letter-phoneme subwords, known as graphones, in several domains to enable detection and recognition of previously unknown words. For these experiments, graphones models are integrated into the SUMMIT speech recognition framework. First, graphones are applied to automatically generate pronunciations of restaurant names for a speech recognizer. Word recognition evaluations show that graphones are effective for generating pronunciations for these words. Next, a graphone hybrid recognizer is built and tested for searching song lyrics by voice, as well as transcribing spoken lectures in a open vocabulary scenario. These experiments demonstrate significant improvement over traditional word-only speech recognizers. Modifications to the flat hybrid model such as reducing the graphone set size are also considered. Finally, a hierarchical hybrid model is built and compared with the flat hybrid model on the lecture transcription task.
by Stanley Xinlei Wang.
M.Eng.
90 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.
Using graphone models in automatic speech recognition
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="e1511277-04b0-4d7c-9049-cafa6dc8d178">
<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>Using graphone models in automatic speech recognition</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2009</PublicationDate>
<Authors>
<Author>
<DisplayName>Wang, Stanley Xinlei</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>This research explores applications of joint letter-phoneme subwords, known as graphones, in several domains to enable detection and recognition of previously unknown words. For these experiments, graphones models are integrated into the SUMMIT speech recognition framework. First, graphones are applied to automatically generate pronunciations of restaurant names for a speech recognizer. Word recognition evaluations show that graphones are effective for generating pronunciations for these words. Next, a graphone hybrid recognizer is built and tested for searching song lyrics by voice, as well as transcribing spoken lectures in a open vocabulary scenario. These experiments demonstrate significant improvement over traditional word-only speech recognizers. Modifications to the flat hybrid model such as reducing the graphone set size are also considered. Finally, a hierarchical hybrid model is built and compared with the flat hybrid model on the lecture transcription task.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>