{"id":"https://openalex.org/W2097068947","doi":"https://doi.org/10.1109/icassp.2013.6637761","title":"Analysis of acoustic-semantic relationship for diversely annotated real-world audio data","display_name":"Analysis of acoustic-semantic relationship for diversely annotated real-world audio data","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2097068947","doi":"https://doi.org/10.1109/icassp.2013.6637761","mag":"2097068947"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6637761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Information and Computer Science, Aalto University, Finland","Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Finland","Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053741868","display_name":"Kalle Palom\u00e4ki","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kalle Palomaki","raw_affiliation_strings":["Department of Information and Computer Science, Aalto University, Finland","Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079981416"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.6431,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70354569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"817"},"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":0.9958999752998352,"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":0.9940999746322632,"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":0.7860521078109741},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6387681365013123},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6264556050300598},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.612754225730896},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5572865605354309},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5104705095291138},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48600253462791443},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4709808826446533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46185529232025146},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41840657591819763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41393864154815674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3424224853515625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32629072666168213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860521078109741},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6387681365013123},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6264556050300598},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.612754225730896},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5572865605354309},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5104705095291138},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48600253462791443},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4709808826446533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46185529232025146},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41840657591819763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41393864154815674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3424224853515625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32629072666168213},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6637761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.5149","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.5149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/%7Emesaros/pubs/mesaros_icassp2013_cr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1677236997","https://openalex.org/W2033178790","https://openalex.org/W2036814807","https://openalex.org/W2089368853","https://openalex.org/W2118230268","https://openalex.org/W2126109423","https://openalex.org/W2148388310","https://openalex.org/W2153146266","https://openalex.org/W2160860215","https://openalex.org/W2404259432","https://openalex.org/W2497516627","https://openalex.org/W2613678836","https://openalex.org/W2977970220","https://openalex.org/W4255838323","https://openalex.org/W6682183282","https://openalex.org/W6683682394","https://openalex.org/W6713534173","https://openalex.org/W6737736267"],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W962203960","https://openalex.org/W2376156759","https://openalex.org/W2026999166","https://openalex.org/W2385868535","https://openalex.org/W1599954583","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349"],"abstract_inverted_index":{"A":[0],"common":[1],"problem":[2],"of":[3,15,57,59,84],"freely":[4],"annotated":[5,76],"or":[6,114],"user":[7],"contributed":[8],"audio":[9,26,30,45],"databases":[10],"is":[11,70,108],"the":[12,16,42,68,85,104,117],"high":[13],"variability":[14],"labels,":[17],"related":[18,106],"to":[19,36],"homonyms,":[20],"synonyms,":[21],"plurals,":[22],"etc.":[23],"Automatically":[24],"re-labeling":[25],"data":[27],"based":[28],"on":[29,109],"similarity":[31,56],"could":[32],"offer":[33],"a":[34,49,99],"solution":[35],"this":[37],"problem.":[38],"This":[39],"paper":[40],"studies":[41],"relationship":[43],"between":[44],"and":[46],"labels":[47,58],"in":[48,93,116],"sound":[50,62],"event":[51,63],"database,":[52],"by":[53],"evaluating":[54],"semantic":[55,118],"acoustically":[60,72,95],"similar":[61,73,79],"instances.":[64],"The":[65],"assumption":[66],"behind":[67],"study":[69],"that":[71],"events":[74],"are":[75],"with":[77],"semantically":[78],"labels.":[80],"Indeed,":[81],"for":[82],"43%":[83],"tested":[86],"data,":[87],"there":[88],"was":[89],"at":[90],"least":[91],"one":[92,111],"ten":[94],"nearest":[96],"neighbors":[97],"having":[98],"synonym":[100],"as":[101],"label,":[102],"while":[103],"closest":[105],"term":[107],"average":[110],"level":[112],"higher":[113],"lower":[115],"hierarchy.":[119]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
