Combination of vector quantization and gaussian mixture models for speaker verification with sparse training data
نویسندگان
چکیده
We present a combination of an extended vector quantization (VQ) algorithm for training a speaker model and a gaussian interpretation of the VQ speaker model in the veri cation phase. This leads to a large decrease of the error rates compared to normal vector quantization and only a slight deterioration compared to full Gaussian mixture model (GMM) training. The training costs of the new method are only slightly higher than for pure vector quantization.
منابع مشابه
Speaker Verification System Based on the Stochastic Modeling
In this paper we propose a new speaker verification system where the new training and classification algorithms for vector quantization and Gaussian mixture models are introduced. The vector quantizer is used to model sub-word speech components. The code books are created for both training and test utterances. We propose new approaches to normalize distortion of the training and test code books...
متن کاملComparative evaluation of maximum a Posteriori vector quantization and gaussian mixture models in speaker verification
Gaussian mixture model with universal background model (GMM–UBM) is a standard reference classifier in speaker verification. We have recently proposed a simplified model using vector quantization (VQ– UBM). In this study, we extensively compare these two classifiers on NIST 2005, 2006 and 2008 SRE corpora, while having a standard discriminative classifier (GLDS–SVM) as a point of reference. We ...
متن کاملComparison between supervised and unsupervised learning of probabilistic linear discriminant analysis mixture models for speaker verification
We present a comparison of speaker verification systems based on unsupervised and supervised mixtures of probabilistic linear discriminant analysis (PLDA) models. This paper explores current applicability of unsupervised mixtures of PLDA models with Gaussian priors in a total variability space for speaker verification. Moreover, we analyze the experimental conditions under which this applicatio...
متن کاملUsing Vector Quantization for Universal Background Model in Automatic Speaker Verification
We aim to describe different approaches for vector quantization in Automatic Speaker Verification. We designed our novel architecture based on multiples codebook representing the speakers and the impostor model called universal background model and compared it to another vector quantization approach used for reducing training data. We compared our scheme with the baseline system, Gaussian Mixtu...
متن کاملSpeaker Identification From Youtube Obtained Data
An efficient, and intuitive algorithm is presented for the identification of speakers from a long dataset (like YouTube long discussion, Cocktail party recorded audio or video).The goal of automatic speaker identification is to identify the number of different speakers and prepare a model for that speaker by extraction, characterization and speaker-specific information contained in the speech s...
متن کامل