{"id":"https://openalex.org/W952524601","doi":null,"title":"AUDIO INFORMATION EXTRACTION FROM ARBITRARY SOUND RECORDINGS","display_name":"AUDIO INFORMATION EXTRACTION FROM ARBITRARY SOUND RECORDINGS","publication_year":2015,"publication_date":"2015-07-14","ids":{"openalex":"https://openalex.org/W952524601","mag":"952524601"},"language":"en","primary_location":{"id":"pmh:oai:usir.salford.ac.uk:34789","doi":null,"is_oa":false,"landing_page_url":"http://usir.salford.ac.uk/id/eprint/34789/1/C__WORK_PhD%20SUpervision_ICSV%20Florence_ICSV22_full_paper_FINAL.pdf","pdf_url":"http://usir.salford.ac.uk/id/eprint/34789/1/C__WORK_PhD%20SUpervision_ICSV%20Florence_ICSV22_full_paper_FINAL.pdf","source":{"id":"https://openalex.org/S4306401501","display_name":"University of Salford Institutional Repository (University of Salford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I54459138","host_organization_name":"University of Salford","host_organization_lineage":["https://openalex.org/I54459138"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5091363316","display_name":"Philip J. Duncan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip J. Duncan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070438187","display_name":"Duraid Y. Mohammed","orcid":"https://orcid.org/0000-0002-9586-1983","observed_orcids":["https://orcid.org/0000-0002-9586-1983"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duraid Y. Mohammed","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9586-1983","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059705422","display_name":"Francis F. Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francis F. Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00861418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"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/audio-classification","display_name":"audio classification","score":0.4790000021457672},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"music information retrieval","score":0.5379999876022339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8799999952316284},{"id":"https://openalex.org/keywords/sound-archives","display_name":"sound archives","score":0.8379999995231628},{"id":"https://openalex.org/keywords/environmental-sounds","display_name":"environmental sounds","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851131558418274},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.612667977809906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5399676561355591},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5014145374298096},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47192028164863586},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43916308879852295},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.42837095260620117},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4280587434768677},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42613571882247925},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4108555316925049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34203821420669556},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31158170104026794},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.178320050239563},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":2,"locations":[{"id":"pmh:oai:usir.salford.ac.uk:34789","doi":null,"is_oa":false,"landing_page_url":"http://usir.salford.ac.uk/id/eprint/34789/1/C__WORK_PhD%20SUpervision_ICSV%20Florence_ICSV22_full_paper_FINAL.pdf","pdf_url":"http://usir.salford.ac.uk/id/eprint/34789/1/C__WORK_PhD%20SUpervision_ICSV%20Florence_ICSV22_full_paper_FINAL.pdf","source":{"id":"https://openalex.org/S4306401501","display_name":"University of Salford Institutional Repository (University of Salford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I54459138","host_organization_name":"University of Salford","host_organization_lineage":["https://openalex.org/I54459138"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"mag:952524601","doi":null,"is_oa":false,"landing_page_url":"https://usir.salford.ac.uk/34789/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W99004151","https://openalex.org/W1495679096","https://openalex.org/W1622490909","https://openalex.org/W1739028175","https://openalex.org/W1891610556","https://openalex.org/W1920779509","https://openalex.org/W1975379835","https://openalex.org/W1991100897","https://openalex.org/W2131981197","https://openalex.org/W2138423018","https://openalex.org/W2148154194","https://openalex.org/W2295807339"],"related_works":["https://openalex.org/W1931509048","https://openalex.org/W2788239956","https://openalex.org/W2772397316","https://openalex.org/W2012603675","https://openalex.org/W2530491586","https://openalex.org/W2148420763","https://openalex.org/W2164266899","https://openalex.org/W4393321377","https://openalex.org/W4246542630","https://openalex.org/W7099697804"],"abstract_inverted_index":{"Numerous":[0],"archives":[1],"of":[2,27,61,72,88,157],"entertainment":[3],"soundtracks":[4],"and":[5,30,45,132,172,178],"other":[6],"recordings":[7,68],"such":[8],"as":[9],"environmental":[10,42],"noise":[11,43],"samples":[12],"have":[13,138],"imposed":[14],"a":[15,86,89,101],"big":[16],"data":[17],"challenge":[18],"in":[19,53,79,112,150,160],"audio":[20,125,163],"related":[21],"industries.":[22],"This":[23,165],"necessitates":[24],"the":[25,54,76,99,105,123,141,155,170,175],"use":[26,60],"machine":[28,151,158],"audition":[29,159],"retrieval":[31,48],"tools":[32,49,63],"to":[33,64,104],"extract":[34],"semantic":[35],"information":[36,47,95,148],"for":[37,56,92],"various":[38],"applications.":[39,181],"Speech":[40],"recognition,":[41],"classification":[44],"music":[46],"haven":[50],"been":[51,110],"developed":[52,111],"past":[55],"specific":[57],"purposes.":[58],"Combined":[59],"these":[62],"process":[65],"arbitrary":[66,93,124],"sound":[67,107],"remains":[69],"challenging:":[70],"overlap":[71],"diverse":[73],"sources":[74,108],"mitigates":[75],"classification,":[77],"resulting":[78],"poor":[80],"recognition":[81],"and/or":[82],"missing":[83],"content.":[84],"Following":[85],"review":[87],"universal":[90],"framework":[91],"soundtrack":[94],"mining":[96],"proposed":[97],"by":[98,115],"authors,":[100],"new":[102,142],"solution":[103],"overlapped":[106],"has":[109],"this":[113],"paper":[114,166],"iterative":[116],"signal":[117],"cleaning":[118],"techniques.":[119],"The":[120],"system":[121],"classifies":[122],"signals":[126],"into":[127],"music,":[128],"speech,":[129],"ambient":[130],"sounds":[131],"silence,":[133],"allowing":[134],"overlap.":[135],"Validation":[136],"tests":[137],"shown":[139],"that":[140],"techniques":[143],"can":[144],"reduce":[145],"or":[146],"eliminate":[147],"losses":[149],"audition,":[152],"hence":[153],"improving":[154],"usability":[156],"processing":[161],"real-world":[162],"archives.":[164],"will":[167],"also":[168],"discuss":[169,179],"dataset":[171],"principles,":[173],"present":[174],"validation":[176],"results":[177],"potential":[180]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2016-06-24T00:00:00"}
