| Autor: |
Julian L. Cárdenas-Barreras, Roberto Díaz-Amador, Eduardo Castillo-Guerra |
| Rok vydání: |
2008 |
| Předmět: |
|
| Zdroj: |
Proceedings of Meetings on Acoustics. |
| ISSN: |
1939-800X |
| DOI: |
10.1121/1.2988044 |
| Popis: |
This paper describes an adaptive threshold estimation mechanism for speaker verification systems. The mechanism estimates speaker-dependent thresholds based on successful verifications considering the minimization of a relation-based cost function. Speaker authentication systems commonly use a threshold to decide whether a claimed identity matches a voice-print previously enrolled. Speaker independent threshold is a common option but it does not consider specific speaker characteristics that are relevant to achieve better system performance. Speaker dependent threshold on the contrary, uses speaker-specific data to estimate individual thresholds but the system performance can also suffer from suboptimal threshold conditioned by the limited number of true scores available in early deployment stages. The algorithm reported in this paper starts with the speaker dependent threshold and use an adaptive algorithm to perform online re-estimation of the initial threshold based on speaker-dependent data. The threshold is re-estimated in each successful authentication transaction according to a custom-made confidence score. The reported technique is more robust to impostor scores and score outliers than traditional speaker dependent threshold. The algorithm provides a performance enhancement of up to 36.2% when compared to traditional speaker independent or dependent thresholds. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
