Show simple item record

dc.contributor.authorShimodaira, Hiroshien
dc.contributor.authorNakai, Mitsuruen
dc.date.accessioned2006-06-22T16:30:45Z
dc.date.available2006-06-22T16:30:45Z
dc.date.issued1993
dc.identifier.citationIn Proc. EuroSpeech'93, pages 1767-1770, Sep 1993.
dc.identifier.urihttp://hdl.handle.net/1842/1286
dc.description.abstractThis paper proposes a novel method for segmenting continuous speech into accent phrases by using a prosodic feature 'pitch pattern'. The pitch pattern extracted from input speech signals is divided into the accent segments automatically by using the One-Stage DP algorithm, in which reference templates representing various types of accent patterns and connectivity between them are used to find out the optimum sequence of accent segments. In case of making the reference templates from a large number of training data, the LBG clustering algorithm is used to represent typical accent patterns by a small number of templates. Evaluation tests were carried out using the ATR continuous speech database of a male speaker. Experimental results showed more than 91 boundaries were correctly detected.en
dc.format.extent90697 bytesen
dc.format.extent340668 bytesen
dc.format.mimetypeapplication/octet-streamen
dc.format.mimetypeapplication/pdfen
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.titleAccent phrase segmentation using transition probabilities between pitch pattern templates.en
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record