Speech Segmentation Using Bayesian Autoregressive Changepoint Detector
View/
Date
1998-12Alternative metrics PlumX
http://hdl.handle.net/11012/58344Altmetrics
Metadata
Show full item recordAbstract
This submission is devoted to the study of the Bayesian autoregressive changepoint detector (BCD) and its use for speech segmentation. Results of the detector application to autoregressive signals as well as to real speech are given. BCD basic properties are described and discussed. The novel two-step algorithm consisting of cepstral analysis and BCD for automatic speech segmentation is suggested.
Keywords
speech segmentation, sub-word boundaries, cepstral analysis, Bayesian methods, changepoint detector, autocorrelationPersistent identifier
http://hdl.handle.net/11012/58344Document type
Peer reviewedDocument version
Final PDFSource
Radioengineering. 1998, vol. 7, č. 4, s. 14-17. ISSN 1210-2512http://www.radioeng.cz/fulltexts/1998/98_04_03.pdf
Collections
- 1998/4 [9]
Citace PRO
Except where otherwise noted, this item's license is described as Creative Commons Attribution 3.0 Unported License