One of the largest challenges in speaker recognition is dealing with speaker-emotion variability problem. Nowadays, compensation techniques are the main solutions to this problem. In these methods, all kinds of speakers’ emotion speech should be elicited thus it is not user-friendly in the application. Therefore the basic problem is how to get the distribution of speakers’ emotion speech and ho...

This work explores the use of DNN/RNN for extracting Baum-Welch sufficient statistics in place of the conventional GMM-UBM in speaker recognition. In this framework, the DNN/RNN is trained for automatic speech recognition (ASR) and each of the output unit corresponds to a component of GMM-UBM. Then the outputs of network are combined with acoustic features to calculate sufficient statistics for...

This paper presents a framework to fit data to a model consisting of multiple connected ellipses. For each iteration of the fitting algorithm, the representation of the multiple ellipses is mapped to a Gaussian mixture model (GMM) and the connections are mapped to geometric constraints for the GMM. The fitting is a modified constrained expectation maximisation (EM) method on the GMM (maximising...

Gaussian mixture models (GMM), trained using the generative criterion of maximum likelihood estimation, have been the most popular approach in speaker recognition during the last decades. This approach is also widely used in many other classification tasks and applications. Generative learning in not however the optimal way to address classification problems. In this paper we first present a ne...

In this paper, we introduce a new approach to dialect recognition which relies on the hypothesis that certain phones are realized differently across dialects. Given a speaker’s utterance, we first obtain the most likely phone sequence using a phone recognizer. We then extract GMM Supervectors for each phone instance. Using these vectors, we design a kernel function that computes the similaritie...

Voice activity detection, i.e., discrimination of the speech/nonspeech segments in a speech signal, is an important enabling technology for a variety of speech-based applications including the speaker recognition. In this work we provide a performance evaluation of the following supervised and unsupervised VAD algorithms in the context of text-dependent speaker recognition on the RSR2015 (Robus...

This paper determines the properties of standard generalized method of moments (GMM) estimators, tests, and confidence sets (CSs) in moment condition models in which some parameters are unidentified or weakly identified in part of the parameter space. The asymptotic distributions of GMM estimators are established under a full range of drifting sequences of true parameters and distributions. The...

Gaussian Mixture Modeling (GMM) is a parametric method for high dimensional density estimation. Incremental learning of GMM is very important in problems such as clustering of streaming data and robot localization in dynamic environments. Traditional GMM estimation algorithms like EM Clustering tend to be computationally very intensive in these scenarios. We present an incremental GMM estimatio...

The system GMM estimator developed by Blundell and Bond (1998) for dynamic panel data models has been widely used in empirical work; however, it does not perform well with weak instruments. This paper proposes a variation on the system GMM estimator, based on a simple transformation of the dependent variable. Simulation results indicate that, in finite samples, this transformed system GMM estim...

This paper presents results on age-group identification (AgeID) for children’s speech, using the OGI Kids corpus and GMM-UBM, GMM-SVM and i-vector systems. Regions of the spectrum containing important age information for children are identified by conducting Age-ID experiments over 21 frequency sub-bands. Results show that the frequencies above 5.5 kHz are least useful for Age-ID. The effect of...