Speaker Verification in the Telephone Network : Research Activities in the CAVE Project
Autor: | Bimbot, F., Hutter, H.-P., Jaboulet, C., Koolwaaij, J.W., Lindberg, J., Pierrot, J.-B., Kokkinakis, G., Fakotakis, N., Dermatas, E. |
---|---|
Přispěvatelé: | Kokkinakis, G., Fakotakis, N., Dermatas, E. |
Předmět: | |
Zdroj: | Kokkinakis, G.; Fakotakis, N.; Dermatas, E. (ed.), Eurospeech '97 Proceedings. ESCA 5th European Conference on Speech Communication and Technology, 971-974. Patras, Greece : TYPOFFSET, K. Manouri-Stanidi STARTPAGE=971;ENDPAGE=974;TITLE=Kokkinakis, G.; Fakotakis, N.; Dermatas, E. (ed.), Eurospeech '97 Proceedings. ESCA 5th European Conference on Speech Communication and Technology Kokkinakis, G.; Fakotakis, N.; Dermatas, E. (ed.), Eurospeech '97 Proceedings. ESCA 5th European Conference on Speech Communication and Technology, pp. 971-974 |
Popis: | This paper summarizes the main results from the Speaker Verification (SV) research pursued so far in the CAVE project. Different state-of-the art SV algorithms were implemented in a common HMM framework and compared on two databases : YOHO (office environment speech) and SESP (telephone speech). This paper is concerned with the different design issues for LR-HMM-based SV algorithms which emerged from our investigations and which led to our current SV system, which delivers Equal Error Rates below 0.5 \% on a very realistic telephone speech database. |
Databáze: | OpenAIRE |
Externí odkaz: |