Effect of Relevance Factor of Maximum a posteriori Adaptation for GMM-SVM in Speaker and Language Recognition
نویسندگان
چکیده
Gaussian mixture model support vector machine (GMMSVM) with nuisance attribute projection (NAP) has been found to be effective and reliable for speaker and language recognition. In maximum a posteriori (MAP) adaptation of GMM, the relevance factor is the parameter that regulates how much the adaptation data affect the base model, which impacts the final recognition performance. In our previous work, the datadependent relevance factor and adaptive relevance factor have been introduced. In this paper, we provide insights into different types of relevance factor for MAP in the context of application as formulated under Speaker Recognition Evaluation (SRE) and Language Recognition Evaluation (LRE) by the National Institute of Standards and Technology (NIST).
منابع مشابه
Bhattacharyya-based GMM-SVM system with adaptive relevance factor for pair language recognition
In this paper, we develop a hybrid system for pair language recognition using Gaussian mixture model (GMM) supervector connecting to support vector machine (SVM). The adaptation of relevance factor in maximum a posteriori (MAP) adaptation of GMM from universal background model (UBM) is studied. In conventional MAP, relevance factor is empirically given by a constant value. It has been proven th...
متن کاملTowards a more efficient SVM supervector speaker verification system using Gaussian reduction and a tree-structured hash
Speaker verification (SV) systems that employ maximum a posteriori (MAP) adaptation of a Gaussian mixture model (GMM) universal background model (UBM) incur a significant teststage computational load in the calculation of a posteriori probabilities and sufficient statistics. We propose a multi-layered hash system employing a tree-structured GMM which uses Runnalls’ GMM reduction technique. The ...
متن کاملStudy on the Relevance Factor of Maximum a Posteriori with GMM for Language Recognition
In this paper, the relevance factor in maximum a posteriori (MAP) adaptation of Gaussian mixture model (GMM) from universal background model (UBM) is studied for language recognition. In conventional MAP, relevance factor is typically set as a constant empirically. Knowing that relevance factor determines how much the observed training data influence the model adaptation, thus the resulting GMM...
متن کاملA hybrid modeling strategy for GMM-SVM speaker recognition with adaptive relevance factor
In Gaussian mixture model (GMM) approach to speaker recognition, it has been found that the maximum a posteriori (MAP) estimation is greatly affected by undesired variability due to varying duration of utterance as well as other hidden factors related to recording devices, session environment, and phonetic contents. We propose an adaptive relevance factor (RF) to compensate for this variability...
متن کاملImproved speaker verification through probabilistic subspace adaptation
In this paper we propose a new adaptation technique for improved text-independent speaker verification with limited amounts of training data using Gaussian mixture models (GMMs). The technique, referred to as probabilistic subspace adaptation (PSA), employs a probabilistic subspace description of how a client’s parametric representation (i.e. GMM) is allowed to vary. Our technique is compared t...
متن کامل