Show simple item record

dc.contributor.authorPadmanabhan, Ananthen
dc.date.accessioned2014-03-14T21:28:06Zen
dc.date.available2014-03-14T21:28:06Zen
dc.date.issued1996en
dc.identifier.otheretd-01312009-063408en
dc.identifier.urihttp://hdl.handle.net/10919/40849en
dc.description.abstractIn this thesis we develop a system for recognition of strings of connected digits that can be used in a hands-free telephone system. We present a detailed description of the elements of the recognition system, such as an endpoint algorithm, the extraction of feature vectors from the speech samples, and the practical issues involved in training and recognition, in a Hidden Markov Model (HMM) based speech recognition system. We use continuous mixture densities to approximate the observation probability density functions (pdfs) in the HMM. While more complex in implementation, continuous (observation) HMMs provide superior performance to the discrete (observation) HMMs. Due to the nature of the application, ours is a speaker dependent recognition system and we have used a single speaker's speech to train and test our system. From the experimental evaluation of the effects of various model sizes on recognition performance, we observed that the use of HMMs with 7 states and 4 mixture density components yields average recognition rates better than 99% on the isolated digits. The level-building algorithm was used with the isolated digit models, which produced a recognition rate of better than 90% for 2-digit strings. For 3 and 4-digit strings, the performance was 83 and 64% respectively. These string recognition rates are much lower than expected for concatenation of single digits. This is most likely due to uncertainties in the location of the concatenated digits, which increases disproportionately with an increase in the number of digits in the string.en
dc.format.extentix, 119 leavesen
dc.format.mediumBTDen
dc.format.mimetypeapplication/pdfen
dc.language.isoenen
dc.publisherVirginia Techen
dc.relation.isformatofOCLC# 36210598en
dc.relation.haspartLD5655.V855_1996.P336.pdfen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectrecognitionen
dc.subjectHMMen
dc.subjectHidden Markov Modelen
dc.subjectcontinuous HMMen
dc.subjectconnected digit recognitionen
dc.subject.lccLD5655.V855 1996.P336en
dc.titleContinuous HMM connected digit recognitionen
dc.typeThesisen
dc.contributor.departmentElectrical Engineeringen
dc.description.degreeMaster of Scienceen
thesis.degree.nameMaster of Scienceen
thesis.degree.levelmastersen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.disciplineElectrical Engineeringen
dc.type.dcmitypeTexten
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-01312009-063408/en
dc.date.sdate2009-01-31en
dc.date.rdate2009-01-31en
dc.date.adate2009-01-31en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record