2026-09-19T11:18:30Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/479062026-06-06T01:04:27Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Christopher M. Schmandt. Molnár, Lajos, 1975- Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2009-10-01T16:01:42Z 2009-10-01T16:01:42Z 1998 1998 http://hdl.handle.net/1721.1/47906 48205509 Thesis (M.Eng. and S.B.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998. Includes bibliographical references (leaves 83-85). This paper describes a text-to-pronunciation system using transformation-based error-driven learning for speech-recognition purposes. Efforts have been made to make the system language independent, automatic, robust and able to generate multiple pronunciations. The learner proposes initial pronunciations for the words and finds transformations that bring the pronunciations closer to the correct pronunciations. The pronunciation generator works by applying the transformations to a similar initial pronunciation. A dynamic aligner is used for the necessary alignment of phonemes and graphemes. The pronunciations are scored using a weighed string edit distance. Optimizations were made to make the learner and the rule applier fast. The system achieves 73.9% exact word accuracy with multiple pronunciations, 82.3% word accuracy with one correct pronunciation, and 95.3% phoneme accuracy for English words. For proper names, it achieves 50.5% exact word accuracy, 69.2% word accuracy, and 92.0% phoneme accuracy, which outperforms the compared neural network approach. Lajos Molnár. M.Eng. S.B. 85 leaves 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. Rule based learning of word pronunciations from training corpora Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="7567bd53-588d-4dc7-aadf-c2a6b2dac87a"> <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>Rule based learning of word pronunciations from training corpora</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>1998</PublicationDate> <Authors> <Author> <DisplayName>Molnár, Lajos, 1975-</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 paper describes a text-to-pronunciation system using transformation-based error-driven learning for speech-recognition purposes. Efforts have been made to make the system language independent, automatic, robust and able to generate multiple pronunciations. The learner proposes initial pronunciations for the words and finds transformations that bring the pronunciations closer to the correct pronunciations. The pronunciation generator works by applying the transformations to a similar initial pronunciation. A dynamic aligner is used for the necessary alignment of phonemes and graphemes. The pronunciations are scored using a weighed string edit distance. Optimizations were made to make the learner and the rule applier fast. The system achieves 73.9% exact word accuracy with multiple pronunciations, 82.3% word accuracy with one correct pronunciation, and 95.3% phoneme accuracy for English words. For proper names, it achieves 50.5% exact word accuracy, 69.2% word accuracy, and 92.0% phoneme accuracy, which outperforms the compared neural network approach.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>