Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish

Detalhes bibliográficos
Autor(a) principal: Vieira, Manuel
Data de Publicação: 2015
Outros Autores: Fonseca, Paulo Jorge, Amorim, Maria Clara Pessoa, Teixeira, Carlos J. C.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.12/5034
Resumo: The study of acoustic communication in animals often requires not only the recognition of species specific acoustic signals but also the identification of individual subjects, all in a complex acoustic background. Moreover, when very long recordings are to be analyzed, automatic recognition and identification processes are invaluable tools to extract the relevant biological information. A pattern recognition methodology based on hidden Markov models is presented inspired by successful results obtained in the most widely known and complex acoustical communication signal: human speech. This methodology was applied here for the first time to the detection and recognition of fish acoustic signals, specifically in a stream of round-the-clock recordings of Lusitanian toadfish (Halobatrachus didactylus) in their natural estuarine habitat. The results show that this methodology is able not only to detect the mating sounds (boatwhistles) but also to identify individual male toadfish, reaching an identification rate of ca. 95%. Moreover this method also proved to be a powerful tool to assess signal durations in large data sets. However, the system failed in recognizing other sound types.
id RCAP_7ed74fce6dcc0a5303353de1b3d7642d
oai_identifier_str oai:repositorio.ispa.pt:10400.12/5034
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfishAnimalsBatrachoidiformesEcosystemHumansMaleMarkov ChainsSound SpectrographySpeech Production MeasurementAcousticsPattern RecognitionSexual BehaviorSignal ProcessingSpeech AcousticsVocalizationThe study of acoustic communication in animals often requires not only the recognition of species specific acoustic signals but also the identification of individual subjects, all in a complex acoustic background. Moreover, when very long recordings are to be analyzed, automatic recognition and identification processes are invaluable tools to extract the relevant biological information. A pattern recognition methodology based on hidden Markov models is presented inspired by successful results obtained in the most widely known and complex acoustical communication signal: human speech. This methodology was applied here for the first time to the detection and recognition of fish acoustic signals, specifically in a stream of round-the-clock recordings of Lusitanian toadfish (Halobatrachus didactylus) in their natural estuarine habitat. The results show that this methodology is able not only to detect the mating sounds (boatwhistles) but also to identify individual male toadfish, reaching an identification rate of ca. 95%. Moreover this method also proved to be a powerful tool to assess signal durations in large data sets. However, the system failed in recognizing other sound types.Fundação para a Ciência e a Tecnologia (FCT)Acoustical Society of AmericaRepositório do ISPAVieira, ManuelFonseca, Paulo JorgeAmorim, Maria Clara PessoaTeixeira, Carlos J. C.2016-11-07T20:04:05Z2015-01-01T00:00:00Z2015-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.12/5034engJournal of the Acoustical Society of America, 138, 3941-3950. Doi: 10.1121/1.49368580001-496610.1121/1.4936858info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2022-09-05T16:40:46Zoai:repositorio.ispa.pt:10400.12/5034Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T15:22:52.220632Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
title Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
spellingShingle Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
Vieira, Manuel
Animals
Batrachoidiformes
Ecosystem
Humans
Male
Markov Chains
Sound Spectrography
Speech Production Measurement
Acoustics
Pattern Recognition
Sexual Behavior
Signal Processing
Speech Acoustics
Vocalization
title_short Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
title_full Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
title_fullStr Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
title_full_unstemmed Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
title_sort Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish
author Vieira, Manuel
author_facet Vieira, Manuel
Fonseca, Paulo Jorge
Amorim, Maria Clara Pessoa
Teixeira, Carlos J. C.
author_role author
author2 Fonseca, Paulo Jorge
Amorim, Maria Clara Pessoa
Teixeira, Carlos J. C.
author2_role author
author
author
dc.contributor.none.fl_str_mv Repositório do ISPA
dc.contributor.author.fl_str_mv Vieira, Manuel
Fonseca, Paulo Jorge
Amorim, Maria Clara Pessoa
Teixeira, Carlos J. C.
dc.subject.por.fl_str_mv Animals
Batrachoidiformes
Ecosystem
Humans
Male
Markov Chains
Sound Spectrography
Speech Production Measurement
Acoustics
Pattern Recognition
Sexual Behavior
Signal Processing
Speech Acoustics
Vocalization
topic Animals
Batrachoidiformes
Ecosystem
Humans
Male
Markov Chains
Sound Spectrography
Speech Production Measurement
Acoustics
Pattern Recognition
Sexual Behavior
Signal Processing
Speech Acoustics
Vocalization
description The study of acoustic communication in animals often requires not only the recognition of species specific acoustic signals but also the identification of individual subjects, all in a complex acoustic background. Moreover, when very long recordings are to be analyzed, automatic recognition and identification processes are invaluable tools to extract the relevant biological information. A pattern recognition methodology based on hidden Markov models is presented inspired by successful results obtained in the most widely known and complex acoustical communication signal: human speech. This methodology was applied here for the first time to the detection and recognition of fish acoustic signals, specifically in a stream of round-the-clock recordings of Lusitanian toadfish (Halobatrachus didactylus) in their natural estuarine habitat. The results show that this methodology is able not only to detect the mating sounds (boatwhistles) but also to identify individual male toadfish, reaching an identification rate of ca. 95%. Moreover this method also proved to be a powerful tool to assess signal durations in large data sets. However, the system failed in recognizing other sound types.
publishDate 2015
dc.date.none.fl_str_mv 2015-01-01T00:00:00Z
2015-01-01T00:00:00Z
2016-11-07T20:04:05Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.12/5034
url http://hdl.handle.net/10400.12/5034
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Journal of the Acoustical Society of America, 138, 3941-3950. Doi: 10.1121/1.4936858
0001-4966
10.1121/1.4936858
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Acoustical Society of America
publisher.none.fl_str_mv Acoustical Society of America
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1817550519020814336