Combining methods to improve speaker veri cation decision
نویسندگان
چکیده
The aim of this paper is to describe how the combination of speaker veri cation algorithms with a priori decision thresholds can improve the overall robustness of a real application. The evaluation is performed in the context of a eld application where each client is veri ed from a 7 digit pin code. This paper demonstrate that it is possible to increase the global performances of the system on combining the result of several algorithms.
منابع مشابه
Combining Methods to Improve Speaker Verification Decision Combining Methods to Improve Speaker Verification Decision
The aim of this paper is to describe how the combination of speaker veri cation al gorithms with a priori decision thresholds can improve the overall robustness of a real application The evaluation is performed in the context of a eld application where each client is veri ed from a digit pin code This paper demonstrate that it is possible to increase the global performances of the system on com...
متن کاملCombining methods to improve speaker verification decision
The aim of this paper is to describe how the combination of speaker veri cation algorithms with a priori decision thresholds can improve the overall robustness of a real application. The evaluation is performed in the context of a eld application where each client is veri ed from a 7 digit pin code. This paper demonstrate that it is possible to increase the global performances of the system on ...
متن کاملTowards better making a decision in speaker verification
Speaker veri!cation is a process that accepts or rejects the identity claim of a speaker. How to make a decision is a critical problem; a threshold for decision-making critically determines performance of a speaker veri!cation system. Traditional threshold estimation methods take only information conveyed by training data into consideration and, to a great extent, do not relate it to production...
متن کاملText Dependent Speaker Verification Using Binary Classifiers Text Dependent Speaker Verification Using Binary Classifiers
This paper describes how a speaker veri cation task can be advantageously decom posed into a series of binary classi cation problems i e each problem discriminating between two classes only Each binary classi er is speci c to one speaker one anti speaker and one word De cision trees dealing with attributes of continuous values are used as classi ers The set of classi ers is then pruned to elimi...
متن کاملCombining Information from Multiple Classiiers for Speaker Veriication
in Proc. of Speaker Recognition and its Commercial and Forensic Applications, France, April 1998. Combining Information from Multiple Classi ers for Speaker Veri cation Sangita Sharma1, Pieter Vermeulen1, Hynek Hermansky1;2 1Oregon Graduate Institute of Science and Technology, Portland, Oregon, USA. 2International Computer Science Institute, Berkeley, California, USA. sangita,pieter,[email protected]...
متن کامل