Successive cohort selection (SCS) for text-independent speaker verification
نویسندگان
چکیده
A novel cohort selection method, namely, successive cohort selection (SCS) is presented in this paper for text-independent speaker verification. The proposed method computes distance between two models directly and it selects new cohort member based on both the claimed speaker model and the existing cohort members. In addition to this new cohort selection method, we also propose a new score measure to be used in verification stage. This new score measure makes use of the absolute score of an utterance to weigh its normalized score in order to further improve the accuracy of a verification. Experimental results on the YOHO speech corpus have revealed that the proposed cohort selection method together with the new score measure reduce the equal-error-rate (EER) of a textindependent system by four times. With only a cohort size of four, the EER of the system is reduced to 0.72%.
منابع مشابه
On cohort selection for speaker verification
Speaker verification systems require some kind of background model to reliably perform the verification task. Several algorithms have been proposed for the selection of cohort models to form a background model. This paper proposes a new cohort selection method called the Close Impostor Clustering (CIC). The new method is shown to outperform several other methods in a text-dependent verification...
متن کاملVulnerability evaluation of speaker verification under voice conversion spoofing: the effect of text constraints
Voice conversion, a technique to change one’s voice to sound like that of another, poses a threat to even high performance speaker verification system. Vulnerability of text-independent speaker verification systems under spoofing attack, using statistical voice conversion technique, was evaluated and confirmed in our previous work. In this paper, we further extend the study to text-dependent sp...
متن کاملGaussian selection applied to text-independent speaker verification
Fast speaker verification systems can be realised by reducing the computation associated with searching of mixture components within the statistical model such as a Gaussian mixture model, GMM. Several improvements regarding computational efficiency have already been proposed for speaker verification. In this paper, the technique of Gaussian selection is applied to the speaker verification task...
متن کاملText-independent speaker verification using rank threshold in large number of speaker models
In this paper, we propose a novel speaker verification method which determines whether a claimer is accepted or rejected by the rank of the claimer in a large number of speaker models instead of score normalization, such as T-norm and Z-norm. The method has advantages over the standard T-norm in speaker verification accuracy. However, it needs much computation time as well as T-norm that needs ...
متن کاملText-independent speaker verification using virtual speaker based cohort normalization
In this paper, we propose a new score normalization method for text-independent speaker verification using GMM (Gaussian Mixture Model). In the proposed method, cohort model is designed as virtual speaker model based on the similarity of local acoustic information between the reference speaker and other customers. The similarity is determined using statistical distance between model components ...
متن کامل