next up previous
Next: ISRL: Improving speech recognition Up: Some of the completed Previous: RULAMO: Rule-Based Language Model


Speaker Verification

Project description:
The aim of this project was to develop a method which evaluates the probability that two given speech signals have been spoken by the same person. The project started from a standard text-dependent speaker verification method that is based on dynamic time warping and cepstral distance measurement. This method assumes that the two speech signals are identically worded. In many practical situations this is not the case, however. Therefore, the two following problems were studied within this project:

Publications related to this project are: [Pfi01], [PB03], [NP04], [GP05], [GKP07], [GBP07], [GP08], and [GKP11].

Supported by: This project was partly supported by NCCR IM2 (i.e. by the Swiss National Science Foundation).

Last updated: Thu Oct 27 14:58:12 CEST 2016 by: Beat Pfister