scholarly journals Automatic Speaker Recognition using MFCC and Artificial Neural Network

2019 ◽  
Vol 9 (1S) ◽  
pp. 39-42
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Speaker Recognition ◽  
Automatic Speaker Recognition ◽  
Extraction Algorithm ◽  
Robust Feature Extraction ◽  
Artificial Neural ◽  
Mel Frequency Cepstral Coefficient ◽  
Feature Extraction Technique

Automatic speaker recognition is the process of identification of a person automatically from his/her voices. A robust feature extraction algorithm is required for effective and efficient classification. In this paper, a new method is proposed for identifying the speaker using an artificial neural network. Here mel- frequency cepstral coefficient(MFCC) is used as a feature extraction technique that provides useful features for the recognition process. Using these extracted features value, input samples are then created and finally, classification is performed using Multilayer Perceptron (MLP) which is trained by backpropagation. This proposed method gives an accuracy of 94.44%.

Development of Quran Reciter Identification System Using MFCC and Neural Network

2016 ◽  
Vol 1 (1) ◽  
pp. 168 ◽  
Author(s):  
Tayseer Mohammed Hasan Asda ◽  
Teddy Surya Gunawan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Identification System ◽  
Successful Match ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Mel Frequency Cepstral Coefficient

Currently, the Quran is recited by so many reciters with different ways and voices.  Some people like to listen to this reciter and others like to listen to other reciters. Sometimes we hear a very nice recitation of al-Quran and want to know who the reciter is. Therefore, this paper is about  the development of Quran reciter recognition and identification system based on Mel Frequency Cepstral Coefficient (MFCC) feature extraction and artificial neural network (ANN). From every speech, characteristics from the utterances will be extracted through neural network model. In this paper a database of five Quran reciters is created and used in training and testing. The feature vector will be fed into Neural Network back propagation learning algorithm for training and identification processes of different speakers. Consequently,  91.2%  of the successful match between targets and input occurred with certain number of hidden layers  which shows how efficient are Mel Frequency Cepstral Coefficient (MFCC) feature extraction  and artificial neural network (ANN) in identifying the reciter voice perfectly.

Sign in / Sign up

Export Citation Format

Share Document