HIERARCHICAL ARABIC PHONEME RECOGNITION USING MFCC ANALYSIS

ABDULADHEM A.; INTESSAR T. HWAIDY

Fulltext

HIERARCHICAL ARABIC PHONEME RECOGNITION USING MFCC ANALYSIS

ABDULADHEM A., INTESSAR T. HWAIDY

Iraqi Journal for Electrical And Electronic Engineering
2007, Volume 3, Issue 1, Pages 97-106

Abstract

In this paper, a hierarchical Arabic phoneme recognition system is proposed in which Mel FrequencyCepstrum Coefficients (MFCC) features is used to train the hierarchical neural networks architecture.Here, separate neural networks (subnetworks) are to be recursively trained to recognize subsets ofphonemes. The overall recognition process is a combination of the outputs of these subnetworks.Experiments that explore the performance of the proposed hierarchical system in comparison to nonhierarchical(flat) baseline systems are also presented in this paper.

Keywords

speech recognition, phoneme recognition, hierarchical systems, Mel cepstrum, neural networks

Year	Total	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
2024	3		1	1	1
2023	15				2		1	1	4	1	2	3	1
2022	45	4	6	3	4	4	3	8	4	4	1	3	1
2021	35		7		1	4	9		3	1	2	2	6
2020	22		3	2	4	2	1	1	2	2	1	4
2019	15	1					3	4	1	2	2	1	1
2018	25		3		2	6	9			1	3	1
2017	23	1	1	1	1	4	2		3		2	3	5
2016	32			4	2	3	5	3	4	3	1	5	2
2015	45	4	5	3	8	5	3	4	1	1	3	6	2
2014	59	2	4	2	6	7		8	2	5	11	8	4
2013	80	12	18	9	10	3	5	6	6	2	2	4	3
2012	34										8	17	9

HIERARCHICAL ARABIC PHONEME RECOGNITION USING MFCC ANALYSIS

Abstract

Keywords

Metrics