Recognizing Arabic Letter Utterance using Convolutional Neural Network

被引：0

作者：

Rajagede, Rian Adam ^{[1
]}

Dewa, Chandra Kusuma ^{[2
]}

Afiahayati ^{[1
]}

机构：

[1] Univ Gadjah Mada, Dept Comp Sci & Elect, Yogyakarta, Indonesia

[2] Univ Islam Indonesia, Dept Informat, Yogyakarta, Indonesia

来源：

2017 18TH IEEE/ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING AND PARALLEL/DISTRIBUTED COMPUTING (SNDP 2017) | 2017年

关键词：

Speech recognition; convolutional neural network; deep neural network;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Arabic letters have unique characteristics because of similarity of sound produced when reciting few letters. This paper present one of application Convolutional Neural Network (CNN) in speech recognition Arabic letters. CNN has shown very good performance for image and speech recognition int the last few years. This study examined the several types of CNN models as well as compare with some Deep Neural Network (DNN) models to speech datasets used. As a result, CNN with a convolution layer and one layer fully-connected managed to obtain an accuracy of up to 80.75%, far better than the traditional DNN that only able to reach 72.0%.

引用

页码：181 / 186

页数：6

共 20 条

[1]

Abdel-Hamid O, 2013, INTERSPEECH, P3365

[2] Convolutional Neural Networks for Speech Recognition [J].

Abdel-Hamid, Ossama ;

Mohamed, Abdel-Rahman ;

Jiang, Hui ;

Deng, Li ;

Penn, Gerald ;

Yu, Dong .

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (10) :1533-1545

[3]

Abdel-Hamid O, 2012, INT CONF ACOUST SPEE, P4277, DOI 10.1109/ICASSP.2012.6288864

[4]

Abriyono, 2012, P INDONESIAN J COMP, V6

[5]

Cai M, 2014, 2014 9TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), P133, DOI 10.1109/ISCSLP.2014.6936676

[6]

Clevert DA., FAST ACCURATE DEEP N

[7]

Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1

[8]

Hassine M., 2015, INT J INTELLIGENT IN, V4, P27

[9]

Hu XH, 2014, 2014 9TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), P15, DOI 10.1109/ISCSLP.2014.6936674

[10]

Huang JT, 2015, INT CONF ACOUST SPEE, P4989, DOI 10.1109/ICASSP.2015.7178920

← 1 2 →