Change search
ReferencesLink to record
Permanent link

Direct link
Statistical properties of the tongue movement during natural speech
KTH, School of Computer Science and Communication (CSC).
2015 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

The objective of this paper is to extract and understand the statistics of tongue movementand analyze the pattern of their movement in free speech.The data used here is the audio signals and sensor readings of the tongue movement offour native English speakers with American accent.Tools from signal processing and probability theory are used to characterize the timeseriescorresponding to the tongue movements. For each speech segment we will create afeature vector corresponding to the spectral properties of the movement. By pooling thesefeatures corresponding to each speech epoch, the principal components of the movementsof different subjects are extracted and studied for their similarity.The transition dynamics will be investigated by creating a transition matrix that woulddescribe the probability of the tongue to move from one location to another in freespeech. Such transition matrices corresponding to the four subjects will be compared fortheir statistical similarities.

Place, publisher, year, edition, pages
National Category
Computer Science
URN: urn:nbn:se:kth:diva-168660OAI: diva2:817824
Available from: 2015-06-06 Created: 2015-06-06 Last updated: 2015-06-06Bibliographically approved

Open Access in DiVA

fulltext(1517 kB)57 downloads
File information
File name FULLTEXT01.pdfFile size 1517 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 57 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 96 hits
ReferencesLink to record
Permanent link

Direct link