Deep neural networks for audio scene recognition

These last years, artificial neural networks (ANN) have known a renewed interest since efficient training procedures have emerged to learn the so called deep neural networks (DNN), i.e. ANN with at least two hidden layers. In the same time, the computational auditory scene recognition (CASR) problem...

Full description

Saved in:
Bibliographic Details
Main Authors: Petetin, Yohan, Laroche, Cyrille, Mayoue, Aurelien
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
audio scene recognition
Context
deep belief networks
Deep neural networks
Europe
Mel frequency cepstral coefficient
Signal processing
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c306t-b53c020d3cefe46c890fc302dc4c7ec806b052a0b12ae7ba67b2a8c9d4c1b6373
cites
container_end_page 129
container_issue
container_start_page 125
container_title
container_volume
creator Petetin, Yohan
Laroche, Cyrille
Mayoue, Aurelien
description These last years, artificial neural networks (ANN) have known a renewed interest since efficient training procedures have emerged to learn the so called deep neural networks (DNN), i.e. ANN with at least two hidden layers. In the same time, the computational auditory scene recognition (CASR) problem which consists in estimating the environment around a device from the received audio signal has been investigated. Most of works which deal with the CASR problem have tried to ind well-adapted features for this problem. However, these features are generally combined with a classical classi-ier. In this paper, we introduce DNN in the CASR ield and we show that such networks can provide promising results and perform better than standard classiiers when the same features are used.
doi_str_mv 10.1109/EUSIPCO.2015.7362358
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_7362358</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7362358</ieee_id><sourcerecordid>7362358</sourcerecordid><originalsourceid>FETCH-LOGICAL-c306t-b53c020d3cefe46c890fc302dc4c7ec806b052a0b12ae7ba67b2a8c9d4c1b6373</originalsourceid><addsrcrecordid>eNotj9FKwzAUQKMgOGa_QB_6A503uc1N8ih1usFggu55JOmtBGc70g7x7x24p_Nw4MAR4kHCQkpwj8vd-_qt2S4USL0wSAq1vRKFMxacU5YUIV6LmQJDlaxJ34piHFMAhTVKIj0T8Mx8LHs-ZX84Y_oZ8tdYdkMu_alNQzlG7rnMHIfPPk1p6O_ETecPIxcXzsXuZfnRrKrN9nXdPG2qiEBTFTRGUNBi5I5ritZBdzaqjXU0HC1QAK08BKk8m-DJBOVtdG0dZSA0OBf3_93EzPtjTt8-_-4vj_gHjDBGDw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Deep neural networks for audio scene recognition</title><source>IEEE Xplore All Conference Series</source><creator>Petetin, Yohan ; Laroche, Cyrille ; Mayoue, Aurelien</creator><creatorcontrib>Petetin, Yohan ; Laroche, Cyrille ; Mayoue, Aurelien</creatorcontrib><description>These last years, artificial neural networks (ANN) have known a renewed interest since efficient training procedures have emerged to learn the so called deep neural networks (DNN), i.e. ANN with at least two hidden layers. In the same time, the computational auditory scene recognition (CASR) problem which consists in estimating the environment around a device from the received audio signal has been investigated. Most of works which deal with the CASR problem have tried to ind well-adapted features for this problem. However, these features are generally combined with a classical classi-ier. In this paper, we introduce DNN in the CASR ield and we show that such networks can provide promising results and perform better than standard classiiers when the same features are used.</description><identifier>EISSN: 2076-1465</identifier><identifier>EISBN: 9780992862633</identifier><identifier>EISBN: 0992862639</identifier><identifier>DOI: 10.1109/EUSIPCO.2015.7362358</identifier><language>eng</language><publisher>EURASIP</publisher><subject>Artificial neural networks ; audio scene recognition ; Context ; deep belief networks ; Deep neural networks ; Europe ; Mel frequency cepstral coefficient ; Signal processing ; Training</subject><ispartof>2015 23rd European Signal Processing Conference (EUSIPCO), 2015, p.125-129</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c306t-b53c020d3cefe46c890fc302dc4c7ec806b052a0b12ae7ba67b2a8c9d4c1b6373</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7362358$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,786,790,795,796,27958,54906,55283</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7362358$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Petetin, Yohan</creatorcontrib><creatorcontrib>Laroche, Cyrille</creatorcontrib><creatorcontrib>Mayoue, Aurelien</creatorcontrib><title>Deep neural networks for audio scene recognition</title><title>2015 23rd European Signal Processing Conference (EUSIPCO)</title><addtitle>EUSIPCO</addtitle><description>These last years, artificial neural networks (ANN) have known a renewed interest since efficient training procedures have emerged to learn the so called deep neural networks (DNN), i.e. ANN with at least two hidden layers. In the same time, the computational auditory scene recognition (CASR) problem which consists in estimating the environment around a device from the received audio signal has been investigated. Most of works which deal with the CASR problem have tried to ind well-adapted features for this problem. However, these features are generally combined with a classical classi-ier. In this paper, we introduce DNN in the CASR ield and we show that such networks can provide promising results and perform better than standard classiiers when the same features are used.</description><subject>Artificial neural networks</subject><subject>audio scene recognition</subject><subject>Context</subject><subject>deep belief networks</subject><subject>Deep neural networks</subject><subject>Europe</subject><subject>Mel frequency cepstral coefficient</subject><subject>Signal processing</subject><subject>Training</subject><issn>2076-1465</issn><isbn>9780992862633</isbn><isbn>0992862639</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2015</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj9FKwzAUQKMgOGa_QB_6A503uc1N8ih1usFggu55JOmtBGc70g7x7x24p_Nw4MAR4kHCQkpwj8vd-_qt2S4USL0wSAq1vRKFMxacU5YUIV6LmQJDlaxJ34piHFMAhTVKIj0T8Mx8LHs-ZX84Y_oZ8tdYdkMu_alNQzlG7rnMHIfPPk1p6O_ETecPIxcXzsXuZfnRrKrN9nXdPG2qiEBTFTRGUNBi5I5ritZBdzaqjXU0HC1QAK08BKk8m-DJBOVtdG0dZSA0OBf3_93EzPtjTt8-_-4vj_gHjDBGDw</recordid><startdate>201508</startdate><enddate>201508</enddate><creator>Petetin, Yohan</creator><creator>Laroche, Cyrille</creator><creator>Mayoue, Aurelien</creator><general>EURASIP</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201508</creationdate><title>Deep neural networks for audio scene recognition</title><author>Petetin, Yohan ; Laroche, Cyrille ; Mayoue, Aurelien</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c306t-b53c020d3cefe46c890fc302dc4c7ec806b052a0b12ae7ba67b2a8c9d4c1b6373</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Artificial neural networks</topic><topic>audio scene recognition</topic><topic>Context</topic><topic>deep belief networks</topic><topic>Deep neural networks</topic><topic>Europe</topic><topic>Mel frequency cepstral coefficient</topic><topic>Signal processing</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Petetin, Yohan</creatorcontrib><creatorcontrib>Laroche, Cyrille</creatorcontrib><creatorcontrib>Mayoue, Aurelien</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Petetin, Yohan</au><au>Laroche, Cyrille</au><au>Mayoue, Aurelien</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Deep neural networks for audio scene recognition</atitle><btitle>2015 23rd European Signal Processing Conference (EUSIPCO)</btitle><stitle>EUSIPCO</stitle><date>2015-08</date><risdate>2015</risdate><spage>125</spage><epage>129</epage><pages>125-129</pages><eissn>2076-1465</eissn><eisbn>9780992862633</eisbn><eisbn>0992862639</eisbn><abstract>These last years, artificial neural networks (ANN) have known a renewed interest since efficient training procedures have emerged to learn the so called deep neural networks (DNN), i.e. ANN with at least two hidden layers. In the same time, the computational auditory scene recognition (CASR) problem which consists in estimating the environment around a device from the received audio signal has been investigated. Most of works which deal with the CASR problem have tried to ind well-adapted features for this problem. However, these features are generally combined with a classical classi-ier. In this paper, we introduce DNN in the CASR ield and we show that such networks can provide promising results and perform better than standard classiiers when the same features are used.</abstract><pub>EURASIP</pub><doi>10.1109/EUSIPCO.2015.7362358</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2076-1465
ispartof 2015 23rd European Signal Processing Conference (EUSIPCO), 2015, p.125-129
issn 2076-1465
language eng
recordid cdi_ieee_primary_7362358
source IEEE Xplore All Conference Series
subjects Artificial neural networks
audio scene recognition
Context
deep belief networks
Deep neural networks
Europe
Mel frequency cepstral coefficient
Signal processing
Training
title Deep neural networks for audio scene recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-21T19%3A41%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Deep%20neural%20networks%20for%20audio%20scene%20recognition&rft.btitle=2015%2023rd%20European%20Signal%20Processing%20Conference%20(EUSIPCO)&rft.au=Petetin,%20Yohan&rft.date=2015-08&rft.spage=125&rft.epage=129&rft.pages=125-129&rft.eissn=2076-1465&rft_id=info:doi/10.1109/EUSIPCO.2015.7362358&rft.eisbn=9780992862633&rft.eisbn_list=0992862639&rft_dat=%3Cieee_CHZPO%3E7362358%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c306t-b53c020d3cefe46c890fc302dc4c7ec806b052a0b12ae7ba67b2a8c9d4c1b6373%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=7362358&rfr_iscdi=true