Computational auditory scene recognition

In this paper, we address the problem of computational auditory scene recognition and describe methods to classify auditory scenes into predefined classes. By auditory scene recognition we mean recognition of an environment using audio information only. The auditory scenes comprised tens of everyday...

Full description

Saved in:
Bibliographic Details
Main Authors: Peltonen, Vesa, Tuomi, Juha, Klapuri, Anssi, Huopaniemi, Jyri, Sorsa, Timo
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Libraries
Mel frequency cepstral coefficient
Rail transportation
Roads
Vehicles
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page II-1944
container_issue
container_start_page II-1941
container_title
container_volume 2
creator Peltonen, Vesa
Tuomi, Juha
Klapuri, Anssi
Huopaniemi, Jyri
Sorsa, Timo
description In this paper, we address the problem of computational auditory scene recognition and describe methods to classify auditory scenes into predefined classes. By auditory scene recognition we mean recognition of an environment using audio information only. The auditory scenes comprised tens of everyday outside and inside environments, such as streets, restaurants, offices, family homes, and cars. Two completely different but almost equally effective classification systems were used: band-energy ratio features with 1-NN classifier and Mel-frequency cepstral coefficients with Gaussian mixture models. The best obtained recognition rate for 17 different scenes out of 26 and for an analysis duration of 30 seconds was 68.4%. For comparison, the recognition accuracy of humans was 70% for 25 different scenes and the average response time was around 20 seconds. The efficiency of different acoustic features and the effect of test sequence length were studied.
doi_str_mv 10.1109/ICASSP.2002.5745009
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_5745009</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5745009</ieee_id><sourcerecordid>5745009</sourcerecordid><originalsourceid>FETCH-LOGICAL-i173t-d5391996a18dd3fd9f7a05bee6af58525a66f4eb1b5779f0cc96e3b2485372a43</originalsourceid><addsrcrecordid>eNotj0tLw0AUhQcfYKz9Bd1k6SbxzvPOXUrQKhQUquCuTJI7MtImJUkX_fdWLBw4iw8O3xFiIaGUEujhtXpcr99LBaBKi8YC0IXIlEYqJMHXpZgTejhFowGFVyKTVkHhpKEbcTuOPwDg0fhM3Ff9bn-YwpT6LmzzcGjT1A_HfGy443zgpv_u0h-8E9cxbEeen3smPp-fPqqXYvW2POmsiiRRT0VrNUkiF6RvWx1bihjA1swuROutssG5aLiWtUWkCE1DjnWtjLcaVTB6Jhb_u4mZN_sh7cJw3JxP6l8w6UPw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Computational auditory scene recognition</title><source>IEEE Xplore All Conference Series</source><creator>Peltonen, Vesa ; Tuomi, Juha ; Klapuri, Anssi ; Huopaniemi, Jyri ; Sorsa, Timo</creator><creatorcontrib>Peltonen, Vesa ; Tuomi, Juha ; Klapuri, Anssi ; Huopaniemi, Jyri ; Sorsa, Timo</creatorcontrib><description>In this paper, we address the problem of computational auditory scene recognition and describe methods to classify auditory scenes into predefined classes. By auditory scene recognition we mean recognition of an environment using audio information only. The auditory scenes comprised tens of everyday outside and inside environments, such as streets, restaurants, offices, family homes, and cars. Two completely different but almost equally effective classification systems were used: band-energy ratio features with 1-NN classifier and Mel-frequency cepstral coefficients with Gaussian mixture models. The best obtained recognition rate for 17 different scenes out of 26 and for an analysis duration of 30 seconds was 68.4%. For comparison, the recognition accuracy of humans was 70% for 25 different scenes and the average response time was around 20 seconds. The efficiency of different acoustic features and the effect of test sequence length were studied.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9780780374027</identifier><identifier>ISBN: 0780374029</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2002.5745009</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial neural networks ; Libraries ; Mel frequency cepstral coefficient ; Rail transportation ; Roads ; Vehicles</subject><ispartof>2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002, Vol.2, p.II-1941-II-1944</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5745009$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,27904,54533,54910</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5745009$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Peltonen, Vesa</creatorcontrib><creatorcontrib>Tuomi, Juha</creatorcontrib><creatorcontrib>Klapuri, Anssi</creatorcontrib><creatorcontrib>Huopaniemi, Jyri</creatorcontrib><creatorcontrib>Sorsa, Timo</creatorcontrib><title>Computational auditory scene recognition</title><title>2002 IEEE International Conference on Acoustics, Speech, and Signal Processing</title><addtitle>ICASSP</addtitle><description>In this paper, we address the problem of computational auditory scene recognition and describe methods to classify auditory scenes into predefined classes. By auditory scene recognition we mean recognition of an environment using audio information only. The auditory scenes comprised tens of everyday outside and inside environments, such as streets, restaurants, offices, family homes, and cars. Two completely different but almost equally effective classification systems were used: band-energy ratio features with 1-NN classifier and Mel-frequency cepstral coefficients with Gaussian mixture models. The best obtained recognition rate for 17 different scenes out of 26 and for an analysis duration of 30 seconds was 68.4%. For comparison, the recognition accuracy of humans was 70% for 25 different scenes and the average response time was around 20 seconds. The efficiency of different acoustic features and the effect of test sequence length were studied.</description><subject>Artificial neural networks</subject><subject>Libraries</subject><subject>Mel frequency cepstral coefficient</subject><subject>Rail transportation</subject><subject>Roads</subject><subject>Vehicles</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9780780374027</isbn><isbn>0780374029</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2002</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj0tLw0AUhQcfYKz9Bd1k6SbxzvPOXUrQKhQUquCuTJI7MtImJUkX_fdWLBw4iw8O3xFiIaGUEujhtXpcr99LBaBKi8YC0IXIlEYqJMHXpZgTejhFowGFVyKTVkHhpKEbcTuOPwDg0fhM3Ff9bn-YwpT6LmzzcGjT1A_HfGy443zgpv_u0h-8E9cxbEeen3smPp-fPqqXYvW2POmsiiRRT0VrNUkiF6RvWx1bihjA1swuROutssG5aLiWtUWkCE1DjnWtjLcaVTB6Jhb_u4mZN_sh7cJw3JxP6l8w6UPw</recordid><startdate>20020101</startdate><enddate>20020101</enddate><creator>Peltonen, Vesa</creator><creator>Tuomi, Juha</creator><creator>Klapuri, Anssi</creator><creator>Huopaniemi, Jyri</creator><creator>Sorsa, Timo</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20020101</creationdate><title>Computational auditory scene recognition</title><author>Peltonen, Vesa ; Tuomi, Juha ; Klapuri, Anssi ; Huopaniemi, Jyri ; Sorsa, Timo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i173t-d5391996a18dd3fd9f7a05bee6af58525a66f4eb1b5779f0cc96e3b2485372a43</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Artificial neural networks</topic><topic>Libraries</topic><topic>Mel frequency cepstral coefficient</topic><topic>Rail transportation</topic><topic>Roads</topic><topic>Vehicles</topic><toplevel>online_resources</toplevel><creatorcontrib>Peltonen, Vesa</creatorcontrib><creatorcontrib>Tuomi, Juha</creatorcontrib><creatorcontrib>Klapuri, Anssi</creatorcontrib><creatorcontrib>Huopaniemi, Jyri</creatorcontrib><creatorcontrib>Sorsa, Timo</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Peltonen, Vesa</au><au>Tuomi, Juha</au><au>Klapuri, Anssi</au><au>Huopaniemi, Jyri</au><au>Sorsa, Timo</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Computational auditory scene recognition</atitle><btitle>2002 IEEE International Conference on Acoustics, Speech, and Signal Processing</btitle><stitle>ICASSP</stitle><date>2002-01-01</date><risdate>2002</risdate><volume>2</volume><spage>II-1941</spage><epage>II-1944</epage><pages>II-1941-II-1944</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9780780374027</isbn><isbn>0780374029</isbn><abstract>In this paper, we address the problem of computational auditory scene recognition and describe methods to classify auditory scenes into predefined classes. By auditory scene recognition we mean recognition of an environment using audio information only. The auditory scenes comprised tens of everyday outside and inside environments, such as streets, restaurants, offices, family homes, and cars. Two completely different but almost equally effective classification systems were used: band-energy ratio features with 1-NN classifier and Mel-frequency cepstral coefficients with Gaussian mixture models. The best obtained recognition rate for 17 different scenes out of 26 and for an analysis duration of 30 seconds was 68.4%. For comparison, the recognition accuracy of humans was 70% for 25 different scenes and the average response time was around 20 seconds. The efficiency of different acoustic features and the effect of test sequence length were studied.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2002.5745009</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1520-6149
ispartof 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002, Vol.2, p.II-1941-II-1944
issn 1520-6149
2379-190X
language eng
recordid cdi_ieee_primary_5745009
source IEEE Xplore All Conference Series
subjects Artificial neural networks
Libraries
Mel frequency cepstral coefficient
Rail transportation
Roads
Vehicles
title Computational auditory scene recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T21%3A35%3A11IST&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=Computational%20auditory%20scene%20recognition&rft.btitle=2002%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech,%20and%20Signal%20Processing&rft.au=Peltonen,%20Vesa&rft.date=2002-01-01&rft.volume=2&rft.spage=II-1941&rft.epage=II-1944&rft.pages=II-1941-II-1944&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9780780374027&rft.isbn_list=0780374029&rft_id=info:doi/10.1109/ICASSP.2002.5745009&rft_dat=%3Cieee_CHZPO%3E5745009%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i173t-d5391996a18dd3fd9f7a05bee6af58525a66f4eb1b5779f0cc96e3b2485372a43%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=5745009&rfr_iscdi=true