Abstract
In a speaker veri¯cation system, a claimed speaker's score is computed to accept or reject the speaker claim. Most of the current methods compute the score as the ratio of the claimed speaker's and the impostors' likelihood functions. Based on analysing false acceptance and false rejection errors obtained by using these methods, we propose a generalised method to ¯nd better scores which can reduce both error types. Proposed scores are the ratios of the functions of the claimed speaker's and the impostors' likelihood functions. Experiments performed on the ANDOSL and YOHO speech corpora show better results for the proposed method.
Original language | English |
---|---|
Pages | 73-76 |
Number of pages | 4 |
Publication status | Published - 2001 |
Event | Speaker Recognition Workshop 2001: A Speaker Odyssey, ODYSSEY 2001 - Crete, Greece Duration: 18 Jun 2001 → 22 Jun 2001 |
Conference
Conference | Speaker Recognition Workshop 2001: A Speaker Odyssey, ODYSSEY 2001 |
---|---|
Country/Territory | Greece |
City | Crete |
Period | 18/06/01 → 22/06/01 |