Title :
Confidence measures in multiple pronunciations modeling for speaker verification
Author :
BenZeghiba, Mohamed F. ; Bourlard, Hervé
Author_Institution :
Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland
Abstract :
The paper investigates the use of multiple pronunciations modeling for user-customized password speaker verification (UCP-SV). The main characteristic of UCP-SV is that the system does not have any a priori knowledge about the password used by the speaker. Our aim is to exploit the information about how the speaker pronounces a password in the decision process. This information is extracted automatically using a speaker-independent speech recognizer. We investigate and compare several techniques. Some of them are based on the combination of confidence scores estimated by different models. In this context, we propose a new confidence measure that uses acoustic information extracted during speaker enrollment and based on a log likelihood ratio measure. These techniques show significant improvement (15.7% relative improvement in terms of equal error rate) compared to a UCP-SV baseline system where the speaker is modeled by only one model (corresponding to one utterance).
Keywords :
parameter estimation; speaker recognition; speech recognition; a priori knowledge; acoustic information; confidence measures; decision process; equal error rate; log likelihood ratio measure; multiple pronunciations modeling; speaker enrollment; speaker-independent speech recognizer; user-customized password speaker verification; Acoustic measurements; Artificial intelligence; Automatic speech recognition; Data mining; Databases; Dictionaries; Error analysis; Hidden Markov models; Loudspeakers; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Print_ISBN :
0-7803-8484-9
DOI :
10.1109/ICASSP.2004.1326004