Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset

The version of record of this article, first published in EURASIP Journal on Audio, Speech, and Music Processing, is available online at Publisher’s website: http://dx.doi.org/10.1186/s13636-019-0152-1

Detalles Bibliográficos
Autores: Benito Gorrón, Diego de, Lozano Díez, Alicia, Torre Toledano, Doroteo, González Rodríguez, Joaquín
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universidad Autónoma de Madrid
Repositorio:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglés
OAI Identifier:oai:repositorio.uam.es:10486/690573
Acceso en línea:http://hdl.handle.net/10486/690573
https://dx.doi.org/10.1186/s13636-019-0152-1
Access Level:acceso abierto
Palabra clave:Acoustic event detection
Music activity detection
Neural networks
Convolutional networks
LSTM
Speech activity detection
Telecomunicaciones
id ES_fb9a6fff24bc82e2283d424ef7798dcf
oai_identifier_str oai:repositorio.uam.es:10486/690573
network_acronym_str ES
network_name_str España
repository_id_str
spelling Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio datasetBenito Gorrón, Diego deLozano Díez, AliciaTorre Toledano, DoroteoGonzález Rodríguez, JoaquínAcoustic event detectionMusic activity detectionNeural networksConvolutional networksLSTMSpeech activity detectionTelecomunicacionesThe version of record of this article, first published in EURASIP Journal on Audio, Speech, and Music Processing, is available online at Publisher’s website: http://dx.doi.org/10.1186/s13636-019-0152-1Audio signals represent a wide diversity of acoustic events, from background environmental noise to spoken communication. Machine learning models such as neural networks have already been proposed for audio signal modeling, where recurrent structures can take advantage of temporal dependencies. This work aims to study the implementation of several neural network-based systems for speech and music event detection over a collection of 77,937 10-second audio segments (216 h), selected from the Google AudioSet dataset. These segments belong to YouTube videos and have been represented as mel-spectrograms. We propose and compare two approaches. The first one is the training of two different neural networks, one for speech detection and another for music detection. The second approach consists on training a single neural network to tackle both tasks at the same time. The studied architectures include fully connected, convolutional and LSTM (long short-term memory) recurrent networks. Comparative results are provided in terms of classification performance and model complexity. We would like to highlight the performance of convolutional architectures, specially in combination with an LSTM stage. The hybrid convolutional-LSTM models achieve the best overall results (85% accuracy) in the three proposed tasks. Furthermore, a distractor analysis of the results has been carried out in order to identify which events in the ontology are the most harmful for the performance of the models, showing some difficult scenarios for the detection of music and speechThis work has been supported by project “DSSL: Redes Profundas y Modelos de Subespacios para Deteccion y Seguimiento de Locutor, Idioma y Enfermedades Degenerativas a partir de la Voz” (TEC2015-68172-C2-1-P), funded by the Ministry of Economy and Competitivity of Spain and FEDERSpringerDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica SuperiorAudio, Data Intelligence and Speech (AUDIAS)20192019-06-17research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/690573https://dx.doi.org/10.1186/s13636-019-0152-1reponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/6905732026-06-23T12:46:27Z
dc.title.none.fl_str_mv Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
title Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
spellingShingle Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
Benito Gorrón, Diego de
Acoustic event detection
Music activity detection
Neural networks
Convolutional networks
LSTM
Speech activity detection
Telecomunicaciones
title_short Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
title_full Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
title_fullStr Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
title_full_unstemmed Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
title_sort Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
dc.creator.none.fl_str_mv Benito Gorrón, Diego de
Lozano Díez, Alicia
Torre Toledano, Doroteo
González Rodríguez, Joaquín
author Benito Gorrón, Diego de
author_facet Benito Gorrón, Diego de
Lozano Díez, Alicia
Torre Toledano, Doroteo
González Rodríguez, Joaquín
author_role author
author2 Lozano Díez, Alicia
Torre Toledano, Doroteo
González Rodríguez, Joaquín
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
Audio, Data Intelligence and Speech (AUDIAS)
dc.subject.none.fl_str_mv Acoustic event detection
Music activity detection
Neural networks
Convolutional networks
LSTM
Speech activity detection
Telecomunicaciones
topic Acoustic event detection
Music activity detection
Neural networks
Convolutional networks
LSTM
Speech activity detection
Telecomunicaciones
description The version of record of this article, first published in EURASIP Journal on Audio, Speech, and Music Processing, is available online at Publisher’s website: http://dx.doi.org/10.1186/s13636-019-0152-1
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-06-17
dc.type.none.fl_str_mv research article
http://purl.org/coar/resource_type/c_2df8fbb1
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10486/690573
https://dx.doi.org/10.1186/s13636-019-0152-1
url http://hdl.handle.net/10486/690573
https://dx.doi.org/10.1186/s13636-019-0152-1
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425344415531008
score 15,301603

Similares en LA Referencia