Analysis, Vocal-tract modeling, and Automatic Detection of Vowel Nasalization

Simple item page
dc.contributor.advisorEspy-Wilson, Carolen_US
dc.contributor.authorPruthi, Tarunen_US
dc.contributor.departmentElectrical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2007-02-07T06:31:01Z
dc.date.available2007-02-07T06:31:01Z
dc.date.issued2007-01-22en_US
dc.description.abstractThe aim of this work is to clearly understand the salient features of nasalization and the sources of acoustic variability in nasalized vowels, and to suggest Acoustic Parameters (APs) for the automatic detection of vowel nasalization based on this knowledge. Possible applications in automatic speech recognition, speech enhancement, speaker recognition and clinical assessment of nasal speech quality have made the detection of vowel nasalization an important problem to study. Although several researchers in the past have found a number of acoustical and perceptual correlates of nasality, automatically extractable APs that work well in a speaker-independent manner are yet to be found. In this study, vocal tract area functions for one American English speaker, recorded using Magnetic Resonance Imaging, were used to simulate and analyze the acoustics of vowel nasalization, and to understand the variability due to velar coupling area, asymmetry of nasal passages, and the paranasal sinuses. Based on this understanding and an extensive survey of past literature, several automatically extractable APs were proposed to distinguish between oral and nasalized vowels. Nine APs with the best discrimination capability were selected from this set through Analysis of Variance. The performance of these APs was tested on several databases with different sampling rates, recording conditions and languages. Accuracies of 96.28%, 77.90% and 69.58% were obtained by using these APs on StoryDB, TIMIT and WS96/97 databases, respectively, in a Support Vector Machine classifier framework. To my knowledge, these results are the best anyone has achieved on this task. These APs were also tested in a cross-language task to distinguish between oral and nasalized vowels in Hindi. An overall accuracy of 63.72% was obtained on this task. Further, the accuracy for phonemically nasalized vowels, 73.40%, was found to be much higher than the accuracy of 53.48% for coarticulatorily nasalized vowels. This result suggests not only that the same APs can be used to capture both phonemic and coarticulatory nasalization, but also that the duration of nasalization is much longer when vowels are phonemically nasalized. This language and category independence is very encouraging since it shows that these APs are really capturing relevant information.en_US
dc.format.extent7185758 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/4273
dc.language.isoen_US
dc.subject.pqcontrolledEngineering, Electronics and Electricalen_US
dc.subject.pqcontrolledLanguage, Linguisticsen_US
dc.subject.pqcontrolledSpeech Communicationen_US
dc.subject.pquncontrolledSpeech Recognitionen_US
dc.subject.pquncontrolledNasalen_US
dc.subject.pquncontrolledVocal tract modelingen_US
dc.subject.pquncontrolledAcoustic parametersen_US
dc.subject.pquncontrolledPhonetic featuresen_US
dc.subject.pquncontrolledHindien_US
dc.titleAnalysis, Vocal-tract modeling, and Automatic Detection of Vowel Nasalizationen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
umi-umd-4144.pdf
Size:
6.85 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Electrical & Computer Engineering Theses and Dissertations