Speech Segmentation Using Bayesian Autoregressive Changepoint Detector
MetadataShow full item record
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.
Keywordsspeech segmentation, sub-word boundaries, cepstral analysis, Bayesian methods, changepoint detector, autocorrelation
Document typePeer reviewed
Document versionFinal PDF
SourceRadioengineering. 1998, vol. 7, č. 4, s. 14-17. ISSN 1210-2512
- 1998/4