Feature trajectory dynamic time warping for clustering of speech segments

Simple item page
dc.contributor.authorLerato, Leratoen_ZA
dc.contributor.authorNiesle, Thomasen_ZA
dc.date.accessioned2019-05-13T07:08:38Z
dc.date.available2019-05-13T07:08:38Z
dc.date.issued2019
dc.descriptionCITATION: Lerato, L. & Niesle, T. 2019. Feature trajectory dynamic time warping for clustering of speech segments. EURASIP Journal on Audio, Speech, and Music Processing, 2019:6, doi:10.1186/s13636-019-0149-9.
dc.descriptionThe original publication is available at https://asmp-eurasipjournals.springeropen.com
dc.description.abstractENGLISH ABSTRACT: Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differinglength. We propose a modification to DTW that performs individual and independent pairwise alignment of featuretrajectories. The modified technique, termed feature trajectory dynamic time warping (FTDTW), is applied as asimilarity measure in the agglomerative hierarchical clustering of speech segments. Experiments using MFCC and PLPparametrisations extracted from TIMIT and from the Spoken Arabic Digit Dataset (SADD) show consistent andstatistically significant improvements in the quality of the resulting clusters in terms of F-measure and normalisedmutual information (NMI).en_ZA
dc.description.urihttps://asmp-eurasipjournals.springeropen.com/articles/10.1186/s13636-019-0149-9
dc.description.versionPublisher's version
dc.format.extent9 pagesen_ZA
dc.identifier.citationLerato, L. & Niesle, T. 2019. Feature trajectory dynamic time warping for clustering of speech segments. EURASIP Journal on Audio, Speech, and Music Processing, 2019:6, doi:10.1186/s13636-019-0149-9
dc.identifier.issn1687-4722 (online)
dc.identifier.issn1687-4714 (print)
dc.identifier.otherdoi:10.1186/s13636-019-0149-9
dc.identifier.urihttp://hdl.handle.net/10019.1/106263
dc.language.isoen_ZAen_ZA
dc.publisherSpringerOpenen_ZA
dc.rights.holderAuthors retain copyrighten_ZA
dc.subjectSpeech segmentsen_ZA
dc.subjectAgglomerations, Industrialen_ZA
dc.subjectHierarchical clustering (Cluster analysis)en_ZA
dc.titleFeature trajectory dynamic time warping for clustering of speech segmentsen_ZA
dc.typeArticleen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
lerato_feature_2019.pdf
Size:
2.17 MB
Format:
Adobe Portable Document Format
Description:
Download article
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Articles (Electrical and Electronic Engineering)