On the convergence of Gaussian mixture models: improvements through vector quantization
نویسندگان
چکیده
This paper studies the reliance of a Gaussian Mixture Model (GMM) based closed-set Speaker Identification system on model convergence and describes methods to improve this convergence. It shows that the reason why the Vector Quantisation GMMs (VQGMMs) outperform a simple GMM is mainly due to decreasing the complexity of the data during training. In addition, it is shown that the VQGMM system is less computationally complex than the traditional GMM, yielding a system which is quicker to train and which gives higher performance. We also investigate four different VQ distance measures which can be used in the training of a VQGMM and compare their respective performances. It is found that the improvements gained by the VQGMM is only marginally dependant on the distance measure.
منابع مشابه
Speaker 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 کاملSpeaker Identification Using Gaussian Mixture Models
In this paper, the performance of Perceptual Linear Prediction (PLP) features has been compared with the performance of Linear Prediction Coefficient (LPC) features for speaker identification. Two classification techniques, Gaussian Mixture Models (GMM) and Vector Quantization (VQ) with Dynamic time wrapping (DTW) are used for classification of speakers based on their speech samples into respec...
متن کاملCombination of vector quantization and gaussian mixture models for speaker verification with sparse training data
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...
متن کاملNetwork Anomaly Detection using Fuzzy Gaussian Mixture Models
Fuzzy Gaussian mixture modeling method is proposed in this paper for network anomaly detection. A mixture of Gaussian distributions was used to represent the network data in multi-dimensional feature space. Gaussian parameters were estimated using fuzzy c-means estimation. The method was tested with the KDD Cup data set. Experimental results have shown that the proposed method is more effective...
متن کاملIdentification of Dynamical Systems Using GMM with VQ Initialization
We are using Gaussian Mixture Models (GMM) as a tool to construct local mappings of nonlinear Multi-Input Multi-Output (MIMO) systems. In this work we combine the advantages of GMM with the Kalman filter. To improve the accuracy of the local linear mappings in a potentially large dimensional state space, we propose to initialize the GMM parameters with Vector Quantization (VQ) or its more parsi...
متن کامل