Show simple item record

dc.contributor.advisorJames R. Glass.en_US
dc.contributor.authorZhang, Yaodong, Ph. D. Massachusetts Institute of Technologyen_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2013-06-17T19:48:20Z
dc.date.available2013-06-17T19:48:20Z
dc.date.copyright2013en_US
dc.date.issued2013en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/79217
dc.descriptionThesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013.en_US
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (p. 163-173).en_US
dc.description.abstractThis thesis is motivated by the challenge of searching and extracting useful information from speech data in a completely unsupervised setting. In many real world speech processing problems, obtaining annotated data is not cost and time effective. We therefore ask how much can we learn from speech data without any transcription. To address this question, in this thesis, we chose the query-by-example spoken term detection as a specific scenario to demonstrate that this task can be done in the unsupervised setting without any annotations. To build the unsupervised spoken term detection framework, we contributed three main techniques to form a complete working flow. First, we present two posteriorgram-based speech representations which enable speaker-independent, and noisy spoken term matching. The feasibility and effectiveness of both posteriorgram features are demonstrated through a set of spoken term detection experiments on different datasets. Second, we show two lower-bounding based methods for Dynamic Time Warping (DTW) based pattern matching algorithms. Both algorithms greatly outperform the conventional DTW in a single-threaded computing environment. Third, we describe the parallel implementation of the lower-bounded DTW search algorithm. Experimental results indicate that the total running time of the entire spoken detection system grows linearly with corpus size. We also present the training of large Deep Belief Networks (DBNs) on Graphical Processing Units (GPUs). The phonetic classification experiment on the TIMIT corpus showed a speed-up of 36x for pre-training and 45x for back-propagation for a two-layer DBN trained on the GPU platform compared to the CPU platform.en_US
dc.description.statementofresponsibilityby Yaodong Zhang.en_US
dc.format.extent173 p.en_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.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.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleUnsupervised speech processing with applications to query-by-example spoken term detectionen_US
dc.typeThesisen_US
dc.description.degreePh.D.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.identifier.oclc844753073en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record