{"id":"https://openalex.org/W2748096539","doi":"https://doi.org/10.1186/s13636-018-0137-5","title":"AudioPairBank: towards a large-scale tag-pair-based audio content analysis","display_name":"AudioPairBank: towards a large-scale tag-pair-based audio content analysis","publication_year":2018,"publication_date":"2018-09-15","ids":{"openalex":"https://openalex.org/W2748096539","doi":"https://doi.org/10.1186/s13636-018-0137-5","mag":"2748096539"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-018-0137-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0137-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0137-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0137-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070436541","display_name":"Sebastian S\u00e4ger","orcid":"https://orcid.org/0000-0002-0283-9075"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sebastian S\u00e4ger","raw_affiliation_strings":["University of Kaiserslautern, DFKI, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"University of Kaiserslautern, DFKI, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, 15213, PA, USA","Carnegie Mellon University, Pittsburgh, USA\u2028"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA\u2028","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Damian Borth","raw_affiliation_strings":["University of Kaiserslautern, DFKI, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"University of Kaiserslautern, DFKI, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062746314","display_name":"Christian Schulze","orcid":"https://orcid.org/0000-0002-2097-422X"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Schulze","raw_affiliation_strings":["University of Kaiserslautern, DFKI, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"University of Kaiserslautern, DFKI, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, 15213, PA, USA","Carnegie Mellon University, Pittsburgh, USA\u2028"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA\u2028","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lane","raw_affiliation_strings":["Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, 15213, PA, USA","Carnegie Mellon University, Pittsburgh, USA\u2028"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA\u2028","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070436541"],"corresponding_institution_ids":["https://openalex.org/I153267046"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.1659,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40520786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2018","issue":"1","first_page":null,"last_page":null},"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":0.995199978351593,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adjective","display_name":"Adjective","score":0.8273168802261353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6967679262161255},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.6670172214508057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5519527792930603},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.5414010286331177},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5371775031089783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44548454880714417},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4174236059188843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3854266107082367},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3256181478500366}],"concepts":[{"id":"https://openalex.org/C2777683214","wikidata":"https://www.wikidata.org/wiki/Q34698","display_name":"Adjective","level":3,"score":0.8273168802261353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967679262161255},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.6670172214508057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5519527792930603},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5414010286331177},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5371775031089783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44548454880714417},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4174236059188843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3854266107082367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3256181478500366},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13636-018-0137-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0137-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0137-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1607.03766","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.03766","pdf_url":"https://arxiv.org/pdf/1607.03766","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2748096539","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1607.03766.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:58ff7e5a039f4655b122e82aedbd8bf4","is_oa":true,"landing_page_url":"https://doaj.org/article/58ff7e5a039f4655b122e82aedbd8bf4","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2018, Iss 1, Pp 1-12 (2018)","raw_type":"article"},{"id":"doi:10.48550/arxiv.1607.03766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1607.03766","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-018-0137-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0137-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0137-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2748096539.pdf","grobid_xml":"https://content.openalex.org/works/W2748096539.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W128363437","https://openalex.org/W193524605","https://openalex.org/W1460854341","https://openalex.org/W1535031652","https://openalex.org/W1757247158","https://openalex.org/W1784731433","https://openalex.org/W1966360794","https://openalex.org/W1972567154","https://openalex.org/W1975325338","https://openalex.org/W1988083194","https://openalex.org/W1989892032","https://openalex.org/W2004906691","https://openalex.org/W2019098406","https://openalex.org/W2025658541","https://openalex.org/W2038484192","https://openalex.org/W2062903088","https://openalex.org/W2064543148","https://openalex.org/W2075456404","https://openalex.org/W2078553167","https://openalex.org/W2093141139","https://openalex.org/W2093650095","https://openalex.org/W2097508275","https://openalex.org/W2106996050","https://openalex.org/W2107471692","https://openalex.org/W2109224087","https://openalex.org/W2110180100","https://openalex.org/W2126412899","https://openalex.org/W2128668540","https://openalex.org/W2130640900","https://openalex.org/W2143483079","https://openalex.org/W2250384498","https://openalex.org/W2290542723","https://openalex.org/W2387119379","https://openalex.org/W2471278348","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W2592436933","https://openalex.org/W2593116425","https://openalex.org/W2775505379","https://openalex.org/W2915649242","https://openalex.org/W2963922351","https://openalex.org/W2964345931","https://openalex.org/W4398958419","https://openalex.org/W6601630192","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W169330724","https://openalex.org/W186475296","https://openalex.org/W2981564799","https://openalex.org/W2392568419","https://openalex.org/W2547461643","https://openalex.org/W2112253750","https://openalex.org/W2966837723","https://openalex.org/W2339576758","https://openalex.org/W1853341420","https://openalex.org/W2787912052","https://openalex.org/W1488381214","https://openalex.org/W2156635423","https://openalex.org/W3090139544","https://openalex.org/W122657243","https://openalex.org/W2150617068","https://openalex.org/W106247045","https://openalex.org/W2785674851","https://openalex.org/W2404510737","https://openalex.org/W49318788","https://openalex.org/W2544134750"],"abstract_inverted_index":{"Recently,":[0],"sound":[1,12],"recognition":[2],"has":[3],"been":[4],"used":[5],"to":[6,62,154],"identify":[7],"sounds,":[8],"such":[9,31,38],"as":[10,32,39],"the":[11,49,63,76,101,118,123,127,147],"of":[13,65,70,80,84,100,105,112,120,146],"a":[14,17,81],"car,":[15],"or":[16],"river.":[18],"However,":[19],"sounds":[20,150],"have":[21,115],"nuances":[22,148],"that":[23],"may":[24],"be":[25],"better":[26],"described":[27],"by":[28],"adjective-noun":[29,56],"pairs":[30,37,57,86],"\u201cslow":[33],"car\u201d":[34],"and":[35,54,58,74,87,103,126,138,151,161],"verb-noun":[36,59],"\u201cflying":[40],"insects,\u201d":[41],"which":[42,132],"are":[43,152],"underexplored.":[44],"Therefore,":[45],"this":[46,93,141],"work":[47],"investigates":[48],"relationship":[50],"between":[51,122],"audio":[52,90,107,124],"content":[53,125],"both":[55],"pairs.":[60],"Due":[61],"lack":[64],"datasets":[66],"with":[67,109],"these":[68,110],"kinds":[69],"annotations,":[71],"we":[72,95],"collected":[73],"processed":[75],"AudioPairBank":[77],"corpus":[78],"consisting":[79],"combined":[82],"total":[83],"1123":[85],"over":[88],"33,000":[89],"files.":[91],"In":[92],"paper,":[94],"include":[96],"previously":[97],"unavailable":[98],"documentation":[99],"challenges":[102],"implications":[104],"collecting":[106],"recordings":[108],"types":[111],"labels.":[113],"We":[114],"also":[116],"shown":[117],"degree":[119],"correlation":[121],"labels":[128],"through":[129],"classification":[130],"experiments,":[131],"yielded":[133],"70%":[134],"accuracy.":[135],"The":[136],"results":[137],"study":[139],"in":[140,149,163],"paper":[142],"encourage":[143],"further":[144],"exploration":[145],"meant":[153],"complement":[155],"similar":[156],"research":[157],"performed":[158],"on":[159],"images":[160],"text":[162],"multimedia":[164],"analysis.":[165]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
