A Dynamic Vocabulary Speech Recognizer Using Real-Time, Associative-Based Learning

dc.contributor.authorPurdy, Trevoren
dc.date.accessioned2006-08-22T14:02:24Z
dc.date.available2006-08-22T14:02:24Z
dc.date.issued2006en
dc.date.submitted2006en
dc.description.abstractConventional speech recognizers employ a training phase during which many of their parameters are configured - including vocabulary selection, feature selection, and decision mechanism tailoring to these selections. After this stage during normal operation, these traditional recognizers do not significantly alter any of these parameters. Conversely this work draws heavily on high level human thought patterns and speech perception to outline a set of precepts to eliminate this training phase and instead opt to perform all its tasks during the normal operation. A feature space model is discussed to establish a set of necessary and sufficient conditions to guide real-time feature selection. Detailed implementation and preliminary results are also discussed. These results indicate that benefits of this approach can be seen in increased speech recognizer adaptability while still retaining competitive recognition rates in controlled environments. Thus this can accommodate such changes as varying vocabularies, class migration, and new speakers.en
dc.formatapplication/pdfen
dc.format.extent606790 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/10012/942
dc.language.isoenen
dc.pendingfalseen
dc.publisherUniversity of Waterlooen
dc.rightsCopyright: 2006, Purdy, Trevor. All rights reserved.en
dc.subjectElectrical & Computer Engineeringen
dc.subjectSpeech Recognitionen
dc.subjectASRen
dc.subjectArtificial Intelligenceen
dc.subjectPattern Recognitionen
dc.titleA Dynamic Vocabulary Speech Recognizer Using Real-Time, Associative-Based Learningen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Applied Scienceen
uws-etd.degree.departmentElectrical and Computer Engineeringen
uws.peerReviewStatusUnrevieweden
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
trpurdy2006.pdf
Size:
592.57 KB
Format:
Adobe Portable Document Format