Cargando…

A hierarchical approach for speech-instrumental-song classification

Audio classification acts as the fundamental step for lots of applications like content based audio retrieval and audio indexing. In this work, we have presented a novel scheme for classifying audio signal into three categories namely, speech, music without voice (instrumental) and music with voice...

Descripción completa

Detalles Bibliográficos
Autores principales: Ghosal, Arijit, Chakraborty, Rudrasis, Dhara, Bibhas Chandra, Saha, Sanjoy Kumar
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2013
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4322669/
https://www.ncbi.nlm.nih.gov/pubmed/25694856
http://dx.doi.org/10.1186/2193-1801-2-526
_version_ 1782356427990368256
author Ghosal, Arijit
Chakraborty, Rudrasis
Dhara, Bibhas Chandra
Saha, Sanjoy Kumar
author_facet Ghosal, Arijit
Chakraborty, Rudrasis
Dhara, Bibhas Chandra
Saha, Sanjoy Kumar
author_sort Ghosal, Arijit
collection PubMed
description Audio classification acts as the fundamental step for lots of applications like content based audio retrieval and audio indexing. In this work, we have presented a novel scheme for classifying audio signal into three categories namely, speech, music without voice (instrumental) and music with voice (song). A hierarchical approach has been adopted to classify the signals. At the first stage, signals are categorized as speech and music using audio texture derived from simple features like ZCR and STE. Proposed audio texture captures contextual information and summarizes the frame level features. At the second stage, music is further classified as instrumental/song based on Mel frequency cepstral co-efficient (MFCC). A classifier based on Random Sample and Consensus (RANSAC), capable of handling wide variety of data has been utilized. Experimental result indicates the effectiveness of the proposed scheme. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1186/2193-1801-2-526) contains supplementary material, which is available to authorized users.
format Online
Article
Text
id pubmed-4322669
institution National Center for Biotechnology Information
language English
publishDate 2013
publisher Springer International Publishing
record_format MEDLINE/PubMed
spelling pubmed-43226692015-02-18 A hierarchical approach for speech-instrumental-song classification Ghosal, Arijit Chakraborty, Rudrasis Dhara, Bibhas Chandra Saha, Sanjoy Kumar Springerplus Methodology Audio classification acts as the fundamental step for lots of applications like content based audio retrieval and audio indexing. In this work, we have presented a novel scheme for classifying audio signal into three categories namely, speech, music without voice (instrumental) and music with voice (song). A hierarchical approach has been adopted to classify the signals. At the first stage, signals are categorized as speech and music using audio texture derived from simple features like ZCR and STE. Proposed audio texture captures contextual information and summarizes the frame level features. At the second stage, music is further classified as instrumental/song based on Mel frequency cepstral co-efficient (MFCC). A classifier based on Random Sample and Consensus (RANSAC), capable of handling wide variety of data has been utilized. Experimental result indicates the effectiveness of the proposed scheme. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1186/2193-1801-2-526) contains supplementary material, which is available to authorized users. Springer International Publishing 2013-10-17 /pmc/articles/PMC4322669/ /pubmed/25694856 http://dx.doi.org/10.1186/2193-1801-2-526 Text en © Ghosal et al.; licensee Springer. 2013 This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Methodology
Ghosal, Arijit
Chakraborty, Rudrasis
Dhara, Bibhas Chandra
Saha, Sanjoy Kumar
A hierarchical approach for speech-instrumental-song classification
title A hierarchical approach for speech-instrumental-song classification
title_full A hierarchical approach for speech-instrumental-song classification
title_fullStr A hierarchical approach for speech-instrumental-song classification
title_full_unstemmed A hierarchical approach for speech-instrumental-song classification
title_short A hierarchical approach for speech-instrumental-song classification
title_sort hierarchical approach for speech-instrumental-song classification
topic Methodology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4322669/
https://www.ncbi.nlm.nih.gov/pubmed/25694856
http://dx.doi.org/10.1186/2193-1801-2-526
work_keys_str_mv AT ghosalarijit ahierarchicalapproachforspeechinstrumentalsongclassification
AT chakrabortyrudrasis ahierarchicalapproachforspeechinstrumentalsongclassification
AT dharabibhaschandra ahierarchicalapproachforspeechinstrumentalsongclassification
AT sahasanjoykumar ahierarchicalapproachforspeechinstrumentalsongclassification
AT ghosalarijit hierarchicalapproachforspeechinstrumentalsongclassification
AT chakrabortyrudrasis hierarchicalapproachforspeechinstrumentalsongclassification
AT dharabibhaschandra hierarchicalapproachforspeechinstrumentalsongclassification
AT sahasanjoykumar hierarchicalapproachforspeechinstrumentalsongclassification