Speaker Verification Using Orthogonal GMM with Fusion of Threshold, Identification Front-end, and UBM
نویسندگان
چکیده
This paper shows that the performance of a Gaussian Mixture Model using a Universal Background Model (GMM-UBM) speaker verification (SV) system can be further improved by combining it with threshold and speaker identification (SI) “front-ends.” The paper formulates performance in terms of false rejection rate and false acceptance rate of the overall SV system. We show analytically that an SI-based front-end can significantly decrease the false acceptance rate and only results in a slight increase in the false rejection rate. Experimentally we use a subset of NIST 2001 speaker recognition corpus with 10 registered speakers of 20 utterances against 10 imposters of 960 utterances. The results show significant reduction in the false acceptance rate, from 3.5% down to 1.0% (i.e. 71% error reduction) while maintaining the same zero false rejection rate.
منابع مشابه
Text Dependent Speaker Verification Using Un-Supervised HMM-UBM and Temporal GMM-UBM
In this paper, we investigate the Hidden Markov Model (HMM) and the temporal Gaussian Mixture Model (GMM) systems based on the Universal Background Model (UBM) concept to capture temporal information of speech for Text Dependent (TD) Speaker Verification (SV). In TD-SV, target speakers are constrained to use only predefined fixed sentence/s during both the enrollment and the test process. The t...
متن کاملText Independent Speaker Modeling and Identification Based On MFCC Features
In this gives an overview of automatic speaker recognition technology, with an emphasis on textindependent recognition. Speaker recognition has been studied actively for several decades. We give an overview of both the classical and the state-of-the-art methods. We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling. Here, describe a ...
متن کاملThe Robustness of GMM-SVM in Real World Applied to Speaker Verification
Gaussian mixture models (GMMs) have proven extremely successful for textindependent speaker verification. The standard training method for GMM models is to use MAP adaptation of the means of the mixture components based on speech from a target speaker. In this work we look into the various models (GMM-UBM and GMM-SVM) and their application to speaker verification. In this paper, features vector...
متن کاملLimited Data Speaker Verification: Fusion of Features
The present work demonstrates experimental evaluation of speaker verification for different speech feature extraction techniques with the constraints of limited data (less than 15 seconds). The state-of-the-art speaker verification techniques provide good performance for sufficient data (greater than 1 minutes). It is a challenging task to develop techniques which perform well for speaker verif...
متن کاملImproving GMM-UBM speaker verification using discriminative feedback adaptation
The Gaussian Mixture Model Universal Background Model (GMM-UBM) system is one of the predominant approaches for text-independent speaker verification, because both the target speaker model and the impostor model (UBM) have generalization ability to handle “unseen” acoustic patterns. However, since GMM-UBM uses a common anti-model, namely UBM, for all target speakers, it tends to be weak in reje...
متن کامل