A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825
Autor(a) principal: | |
---|---|
Data de Publicação: | 2013 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por eng |
Título da fonte: | Acta scientiarum. Technology (Online) |
Texto Completo: | http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825 |
Resumo: | Recognition of isolated spoken digits is the core procedure for a large number of applications which rely solely on speech for data exchange, as in telephone-based services, such as dialing, airline reservation, bank transaction and price quotation. Spoken digit recognition is generally a challenging task since the signals last for a short period of time and often some digits are acoustically very similar to other digits. The objective of this paper is to investigate the use of machine learning algorithms for spoken digit recognition and disclose the free availability of a database with digits pronounced in English and Portuguese to the scientific community. Since machine learning algorithms are fully dependent on predictive attributes to build precise classifiers, we believe that the most important task for successfully recognizing spoken digits is feature extraction. In this work, we show that Line Spectral Frequencies (LSF) provide a set of highly predictive coefficients. We evaluated our classifiers in different settings by altering the sampling rate to simulate low quality channels and varying the number of coefficients. |
id |
UEM-6_add49bbfd277214c3875c6463d9275a8 |
---|---|
oai_identifier_str |
oai:periodicos.uem.br/ojs:article/19825 |
network_acronym_str |
UEM-6 |
network_name_str |
Acta scientiarum. Technology (Online) |
repository_id_str |
|
spelling |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825spoken digit recognitionmel-frequency cepstrum coefficientsline spectral frequencies.Ciência da ComputaçãoRecognition of isolated spoken digits is the core procedure for a large number of applications which rely solely on speech for data exchange, as in telephone-based services, such as dialing, airline reservation, bank transaction and price quotation. Spoken digit recognition is generally a challenging task since the signals last for a short period of time and often some digits are acoustically very similar to other digits. The objective of this paper is to investigate the use of machine learning algorithms for spoken digit recognition and disclose the free availability of a database with digits pronounced in English and Portuguese to the scientific community. Since machine learning algorithms are fully dependent on predictive attributes to build precise classifiers, we believe that the most important task for successfully recognizing spoken digits is feature extraction. In this work, we show that Line Spectral Frequencies (LSF) provide a set of highly predictive coefficients. We evaluated our classifiers in different settings by altering the sampling rate to simulate low quality channels and varying the number of coefficients. Universidade Estadual De Maringá2013-05-23info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionanálise experimentalapplication/pdfapplication/pdfhttp://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/1982510.4025/actascitechnol.v35i4.19825Acta Scientiarum. Technology; Vol 35 No 4 (2013); 621-628Acta Scientiarum. Technology; v. 35 n. 4 (2013); 621-6281806-25631807-8664reponame:Acta scientiarum. Technology (Online)instname:Universidade Estadual de Maringá (UEM)instacron:UEMporenghttp://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825/pdfhttp://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825/pdf_1Silva, Diego FurtadoSouza, Vinícius Mourão Alves deBatista, Gustavo Enrique Almeida Prado Alvesinfo:eu-repo/semantics/openAccess2024-05-17T13:03:40Zoai:periodicos.uem.br/ojs:article/19825Revistahttps://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/indexPUBhttps://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/oai||actatech@uem.br1807-86641806-2563opendoar:2024-05-17T13:03:40Acta scientiarum. Technology (Online) - Universidade Estadual de Maringá (UEM)false |
dc.title.none.fl_str_mv |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
title |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
spellingShingle |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 Silva, Diego Furtado spoken digit recognition mel-frequency cepstrum coefficients line spectral frequencies. Ciência da Computação |
title_short |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
title_full |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
title_fullStr |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
title_full_unstemmed |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
title_sort |
A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English - doi: 10.4025/actascitechnol.v35i4.19825 |
author |
Silva, Diego Furtado |
author_facet |
Silva, Diego Furtado Souza, Vinícius Mourão Alves de Batista, Gustavo Enrique Almeida Prado Alves |
author_role |
author |
author2 |
Souza, Vinícius Mourão Alves de Batista, Gustavo Enrique Almeida Prado Alves |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Silva, Diego Furtado Souza, Vinícius Mourão Alves de Batista, Gustavo Enrique Almeida Prado Alves |
dc.subject.por.fl_str_mv |
spoken digit recognition mel-frequency cepstrum coefficients line spectral frequencies. Ciência da Computação |
topic |
spoken digit recognition mel-frequency cepstrum coefficients line spectral frequencies. Ciência da Computação |
description |
Recognition of isolated spoken digits is the core procedure for a large number of applications which rely solely on speech for data exchange, as in telephone-based services, such as dialing, airline reservation, bank transaction and price quotation. Spoken digit recognition is generally a challenging task since the signals last for a short period of time and often some digits are acoustically very similar to other digits. The objective of this paper is to investigate the use of machine learning algorithms for spoken digit recognition and disclose the free availability of a database with digits pronounced in English and Portuguese to the scientific community. Since machine learning algorithms are fully dependent on predictive attributes to build precise classifiers, we believe that the most important task for successfully recognizing spoken digits is feature extraction. In this work, we show that Line Spectral Frequencies (LSF) provide a set of highly predictive coefficients. We evaluated our classifiers in different settings by altering the sampling rate to simulate low quality channels and varying the number of coefficients. |
publishDate |
2013 |
dc.date.none.fl_str_mv |
2013-05-23 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion análise experimental |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825 10.4025/actascitechnol.v35i4.19825 |
url |
http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825 |
identifier_str_mv |
10.4025/actascitechnol.v35i4.19825 |
dc.language.iso.fl_str_mv |
por eng |
language |
por eng |
dc.relation.none.fl_str_mv |
http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825/pdf http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/19825/pdf_1 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Estadual De Maringá |
publisher.none.fl_str_mv |
Universidade Estadual De Maringá |
dc.source.none.fl_str_mv |
Acta Scientiarum. Technology; Vol 35 No 4 (2013); 621-628 Acta Scientiarum. Technology; v. 35 n. 4 (2013); 621-628 1806-2563 1807-8664 reponame:Acta scientiarum. Technology (Online) instname:Universidade Estadual de Maringá (UEM) instacron:UEM |
instname_str |
Universidade Estadual de Maringá (UEM) |
instacron_str |
UEM |
institution |
UEM |
reponame_str |
Acta scientiarum. Technology (Online) |
collection |
Acta scientiarum. Technology (Online) |
repository.name.fl_str_mv |
Acta scientiarum. Technology (Online) - Universidade Estadual de Maringá (UEM) |
repository.mail.fl_str_mv |
||actatech@uem.br |
_version_ |
1799315335386497024 |