Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)

Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)

In this paper, the Mel-Frequency Cepstral Coefficient (MFCC) is demonstrated as an effective feature representation method for spoken letters recognition. The Multi-Layer Perceptron (MLP) was used as a classifier to discriminate between two spoken letters - 'A' and 'S'. The datas...

Full description

Bibliographic Details
Published in:ICCAIE 2011 - 2011 IEEE Conference on Computer Applications and Industrial Electronics
Main Author: Daud M.S.; Yassin I.M.; Zabidi A.; Johari M.A.; Salleh M.K.M.
Format: Conference paper
Language:English
Published: 2011
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84858756069&doi=10.1109%2fICCAIE.2011.6162096&partnerID=40&md5=b968932fde18023db818c50bd2e5437d
id 2-s2.0-84858756069
spelling 2-s2.0-84858756069
Daud M.S.; Yassin I.M.; Zabidi A.; Johari M.A.; Salleh M.K.M.
Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
2011
ICCAIE 2011 - 2011 IEEE Conference on Computer Applications and Industrial Electronics


10.1109/ICCAIE.2011.6162096
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84858756069&doi=10.1109%2fICCAIE.2011.6162096&partnerID=40&md5=b968932fde18023db818c50bd2e5437d
In this paper, the Mel-Frequency Cepstral Coefficient (MFCC) is demonstrated as an effective feature representation method for spoken letters recognition. The Multi-Layer Perceptron (MLP) was used as a classifier to discriminate between two spoken letters - 'A' and 'S'. The dataset consists of 72 samples (35 and 37 samples of spoken letters 'A' and 'S', respectively). The samples were represented using the Mel Frequency Cepstral Coefficients (MFCC). Several experiments were conducted to determine the optimal network parameters to yield the best classification results. The results indicate that the optimal network structure was with 2 hidden units, which yielded classification accuracy of 100% (training) and 93% (testing). © 2011 IEEE.


English
Conference paper
author Daud M.S.; Yassin I.M.; Zabidi A.; Johari M.A.; Salleh M.K.M.
spellingShingle Daud M.S.; Yassin I.M.; Zabidi A.; Johari M.A.; Salleh M.K.M.
Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
author_facet Daud M.S.; Yassin I.M.; Zabidi A.; Johari M.A.; Salleh M.K.M.
author_sort Daud M.S.; Yassin I.M.; Zabidi A.; Johari M.A.; Salleh M.K.M.
title Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
title_short Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
title_full Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
title_fullStr Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
title_full_unstemmed Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
title_sort Investigation of MFCC feature representation for classification of spoken letters using Multi-Layer Perceptrons (MLP)
publishDate 2011
container_title ICCAIE 2011 - 2011 IEEE Conference on Computer Applications and Industrial Electronics
container_volume
container_issue
doi_str_mv 10.1109/ICCAIE.2011.6162096
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-84858756069&doi=10.1109%2fICCAIE.2011.6162096&partnerID=40&md5=b968932fde18023db818c50bd2e5437d
description In this paper, the Mel-Frequency Cepstral Coefficient (MFCC) is demonstrated as an effective feature representation method for spoken letters recognition. The Multi-Layer Perceptron (MLP) was used as a classifier to discriminate between two spoken letters - 'A' and 'S'. The dataset consists of 72 samples (35 and 37 samples of spoken letters 'A' and 'S', respectively). The samples were represented using the Mel Frequency Cepstral Coefficients (MFCC). Several experiments were conducted to determine the optimal network parameters to yield the best classification results. The results indicate that the optimal network structure was with 2 hidden units, which yielded classification accuracy of 100% (training) and 93% (testing). © 2011 IEEE.
publisher
issn
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1809678489623724032

Similar Items