earticle

영어

Speech recognition is a challenging yet important speech technology. First, an introduction proposes components of typical automatic speaker recognition system .Two modes like enrollment mode and recognition is discussed. Then we discuss about Feature Extraction [8] .It is used to reduce the dimensionality of the input vector while maintaining the discriminating power of signal. After this Gaussian mixture modeling is discussed, which is the speaker modeling technique used in most systems. Vector Quantization Process is also discussed and then paper highlights on Supervectors. A few speaker modeling alternatives, namely, neural networks and support vector machines, are mentioned. Most recent technique to solve the Speaker Verification System is to combine GMM with SVM .So GMM Supervector [3] is also discussed. Here GMM supervector based SVM is applied to this field with spectral features. A GMM is trained for each utterance, and the corresponding GMM supervector is used as the input feature for SVM. Then, some applications of speaker verification are proposed, including on-site applications, remote applications, applications relative to structuring audio information, and games.