Modified Technique for Speaker Recognition using ANN
نویسندگان
چکیده
Speaker recognition consists of three phases: pre-processing, feature extraction and classification. During the first phase, the computer records the voice pattern of the speaker and analyse it. By the end of the second phase, the main features of the voice pattern are extracted. In the third phase, many classification techniques are exist such as artificial neural network (ANN) , hidden Markov model (HMM) and vector quantization (VQ). Classifiers based on ANN are used in both text dependent and text independent speaker identification and speaker verification systems. Furthermore, it is extremely efficient at learning complex mappings between input and outputs. Unfortunately, ANN technique is complex and time consuming. In this paper, we use two different feature extraction techniques. These techniques are MFCC and PNCC. In addition, we use principle component analysis (PCA) as a feature reduction technique to enhance the classifier performance and speed. We apply ANN for both techniques with different training algorithms. The best results are achieved using PNCC as a feature extraction, the ANN as a classifier with sequential weight/bias training algorithm. Our proposed technique decreases the number of neurons that lead to have best performance and processing time.
منابع مشابه
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...
متن کاملSpeaker 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...
متن کاملSpeaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words
متن کامل
Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words
متن کامل
MFCC Based Text-Dependent Speaker Identification Using BPNN
Speech processing has emerged as one of the important application area of digital signal processing. Various fields for research in speech processing are speech recognition, speaker recognition, speech synthesis, speech coding etc. Speaker recognition is one of the most useful and popular biometric recognition techniques in the world especially related to areas in which security is a major conc...
متن کامل