Theory for speaker recognition over IP

Methodology for Evaluating Speaker Verification Robustness over Ip Networks

In the framework of biometric person authentication over Internet, speech and more precisely speaker recognition play an important role. Internet is an application context relatively new for speech and speaker recognition and several new questions appear with it. This paper presents the efforts of COST 275 action and ELISA consortium in the field of performance assessment. Two points are partic...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Reviewing Speaker Recognition Influence in Strengthening VOIP Caller Authentication

This paper focuses on authentication issues and user ID detection depending on the voice signature of the incoming Voice over IP (VoIP) calls. Firstly, a complete speaker recognition system based on LPC feature extraction and decision based on Artificial Neural Network was described and built using MATLAB package. Then, MATLAB package was used to develop a simplified prototype version of the mo...