{"id":"https://openalex.org/W2010486494","doi":"https://doi.org/10.1145/1460096.1460115","title":"Large-scale content-based audio retrieval from text queries","display_name":"Large-scale content-based audio retrieval from text queries","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2010486494","doi":"https://doi.org/10.1145/1460096.1460115","mag":"2010486494"},"language":"en","primary_location":{"id":"doi:10.1145/1460096.1460115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1460096.1460115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM international conference on Multimedia information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gal Chechik","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013936779","display_name":"Eugene Ie","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Ie","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076439350","display_name":"Martin Rehn","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Rehn","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samy Bengio","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064141702","display_name":"Dick Lyon","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dick Lyon","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045719865"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":9.116,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.9829316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8769665956497192},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7713347673416138},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6026726365089417},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49933528900146484},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.46701982617378235},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.46083882451057434},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45613154768943787},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4520050883293152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39055120944976807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3491382300853729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3373463749885559},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15488600730895996},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14375218749046326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769665956497192},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7713347673416138},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6026726365089417},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49933528900146484},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.46701982617378235},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46083882451057434},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45613154768943787},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4520050883293152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39055120944976807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3491382300853729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3373463749885559},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15488600730895996},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14375218749046326},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1460096.1460115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1460096.1460115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM international conference on Multimedia information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.146.4379","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.4379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.stanford.edu/~gal/Papers/chechik_MIR2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.306.4925","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.306.4925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bengio.abracadoudou.com/publications/pdf/chechik_2008_mir.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.3108","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.3108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/33429.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W97874008","https://openalex.org/W1560013842","https://openalex.org/W1660390307","https://openalex.org/W1852256319","https://openalex.org/W2007835025","https://openalex.org/W2041823554","https://openalex.org/W2047221353","https://openalex.org/W2100969003","https://openalex.org/W2116373735","https://openalex.org/W2127781398","https://openalex.org/W2133999183","https://openalex.org/W2141282920","https://openalex.org/W2154016477","https://openalex.org/W2156909104","https://openalex.org/W2160218441","https://openalex.org/W2170741935","https://openalex.org/W2916567321","https://openalex.org/W6682395106","https://openalex.org/W6683584131","https://openalex.org/W6759319768"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2768810474"],"abstract_inverted_index":{"In":[0,38],"content-based":[1,19],"audio":[2,69,86],"retrieval,":[3],"the":[4],"goal":[5],"is":[6,51],"to":[7,81,126],"find":[8],"sound":[9,62,102],"recordings":[10],"(audio":[11],"documents)":[12],"based":[13,64,114],"on":[14,115],"their":[15],"acoustic":[16],"features.":[17],"This":[18],"approach":[20,46,113],"differs":[21],"from":[22],"retrieval":[23,121],"approaches":[24],"that":[25,50,54],"index":[26],"media":[27],"files":[28],"using":[29],"metadata":[30],"such":[31],"as":[32],"file":[33],"names":[34],"and":[35,77,88,106,123,134],"user":[36],"tags.":[37],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,98,111,116],"machine":[44],"learning":[45],"for":[47,119],"retrieving":[48],"sounds":[49],"novel":[52],"in":[53],"it":[55,125],"(1)":[56],"uses":[57],"free-form":[58],"text":[59],"queries":[60],"rather":[61,71],"sample":[63],"queries,":[65],"(2)":[66],"searches":[67],"by":[68],"content":[70],"than":[72],"via":[73],"textual":[74],"meta":[75],"data,":[76],"(3)":[78],"can":[79],"scale":[80],"very":[82,89],"large":[83],"number":[84],"of":[85,101],"documents":[87],"rich":[90],"query":[91],"vocabulary.":[92],"We":[93,109],"handle":[94],"generic":[95],"sounds,":[96],"including":[97],"wide":[99],"variety":[100],"effects,":[103],"animal":[104],"vocalizations":[105],"natural":[107],"scenes.":[108],"test":[110],"scalable":[112],"passive-aggressive":[117],"model":[118],"image":[120],"(PAMIR),":[122],"compare":[124],"two":[127],"state-of-the-art":[128],"approaches;":[129],"Gaussian":[130],"mixture":[131],"models":[132],"(GMM)":[133],"support":[135],"vector":[136],"machines":[137],"(SVM).":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
