2026-09-19T13:14:15Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/386842022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

James R. Glass. Park, Alex S. (Alex Seungryong), 1979- Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2007-08-29T20:44:36Z 2007-08-29T20:44:36Z 2006 2007 http://hdl.handle.net/1721.1/38684 164437217 Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2007. Includes bibliographical references (p. 167-176). We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to classify speech into categories defined by a pre-specified inventory of lexical units (i.e. phones or words). Instead, we attempt to discover such an inventory in an unsupervised manner by exploiting the structure of repeating patterns within the speech signal. We show how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream. Our approach to unsupervised word acquisition utilizes a segmental variant of a widely used dynamic programming technique, which allows us to find matching acoustic patterns between spoken utterances. By aggregating information about these matching patterns across audio streams, we demonstrate how to group similar acoustic sequences together to form clusters corresponding to lexical entities such as words and short multi-word phrases. On a corpus of academic lecture material, we demonstrate that clusters found using this technique exhibit high purity and that many of the corresponding lexical identities are relevant to the underlying audio stream. (cont.) We demonstrate two applications of our pattern discovery procedure. First, we propose and evaluate two methods for automatically identifying sound clusters generated through pattern discovery. Our results show that high identification accuracy can be achieved for single word clusters using a constrained isolated word recognizer. Second, we apply acoustic pattern matching to the problem of speaker segmentation by attempting to find word-level speech patterns that are repeated by the same speaker. When used to segment a ten hour corpus of multi-speaker lectures, we found that our approach is able to generate segmentations that correlate well to independently generated human segmentations. by Alex Seungryong Park. Ph.D. 176 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. Unsupervised pattern discovery in speech : applications to word acquisition and speaker segmentation Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="23f3420b-8446-4455-b67a-3e7911bcd60a"> <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>Unsupervised pattern discovery in speech : applications to word acquisition and speaker segmentation</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2007</PublicationDate> <Authors> <Author> <DisplayName>Park, Alex S. (Alex Seungryong), 1979-</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>We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to classify speech into categories defined by a pre-specified inventory of lexical units (i.e. phones or words). Instead, we attempt to discover such an inventory in an unsupervised manner by exploiting the structure of repeating patterns within the speech signal. We show how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream. Our approach to unsupervised word acquisition utilizes a segmental variant of a widely used dynamic programming technique, which allows us to find matching acoustic patterns between spoken utterances. By aggregating information about these matching patterns across audio streams, we demonstrate how to group similar acoustic sequences together to form clusters corresponding to lexical entities such as words and short multi-word phrases. On a corpus of academic lecture material, we demonstrate that clusters found using this technique exhibit high purity and that many of the corresponding lexical identities are relevant to the underlying audio stream.</Abstract> <Abstract>(cont.) We demonstrate two applications of our pattern discovery procedure. First, we propose and evaluate two methods for automatically identifying sound clusters generated through pattern discovery. Our results show that high identification accuracy can be achieved for single word clusters using a constrained isolated word recognizer. Second, we apply acoustic pattern matching to the problem of speaker segmentation by attempting to find word-level speech patterns that are repeated by the same speaker. When used to segment a ten hour corpus of multi-speaker lectures, we found that our approach is able to generate segmentations that correlate well to independently generated human segmentations.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>