DMCA
Speaker verification over the telephone (2000)
| Citations: | 14 - 4 self |
BibTeX
@MISC{Lamel00speakerverification,
author = {L. F. Lamel and J. L. Gauvain},
title = { Speaker verification over the telephone },
year = {2000}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Speaker verification has been the subject of active research for many years, yet despite these efforts and promising results on laboratory data, speaker verification performance over the telephone remains below that required for many applications. This experimental study aimed to quantify speaker recognition performance out of the context of any specific application, as a function of factors more-or-less acknowledged to affect the accuracy. Some of the issues addressed are: the speaker model (Gaussian mixture models are compared with phone-based models), the influence of the amount and content of training and test data on performance; performance degradation due to model aging and how can this be counteracted by using adaptation techniques; achievable performance levels using text-dependent and text-independent recognition modes. These and other factors were addressed using a large corpus of read and spontaneous speech (over 250 hours collected from 100 target speakers and 1000 imposters) in French, designed and recorded for the purpose of this study. On these data, the lowest equal error rate is 1 % for the text-dependent mode when two trials are allowed per verification attempt and with a minimum of 1.5 s of speech per trial.
Keyphrases
speaker verification test data many application experimental study many year phone-based model speaker model specific application verification attempt speaker verification performance adaptation technique text-independent recognition mode active research speaker recognition performance large corpus spontaneous speech gaussian mixture model target speaker performance degradation equal error rate text-dependent mode laboratory data achievable performance level
