Development of Quran reciter identification system using MFCC and neural network
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 d...
Saved in:
| Main Authors: | , , , |
|---|---|
| 格式: | Article |
| 语言: | English English |
| 出版: |
Institute of Advanced engineering and Science (IAES)
2016
|
| 主题: | |
| 在线阅读: | http://irep.iium.edu.my/51467/ http://irep.iium.edu.my/51467/ http://irep.iium.edu.my/51467/ http://irep.iium.edu.my/51467/1/18_updated16_16Nov15_9114_Development_of_Quran_Reciter.pdf http://irep.iium.edu.my/51467/4/51467_Development%20of%20Quran%20reciter%20_Scopus.pdf |
| 标签: |
添加标签
没有标签, 成为第一个标记此记录!
|
| 总结: | 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. |
|---|