Conference paper

User-Customized Password HMM Based Speaker Verification

is presented. The system has no {\it a priori} knowledge of passwords. A hybrid HMM/ANN system is used to infer the phonetic transcription of the password. The emission probabilities are then modeled by a multi-Gaussians HMM model. Evaluation experiments, conducted on PolyVar database, showed results comparable with a system where the correct phonetic transcription of the password is known {\it a priori}.

Related material