{"id":"https://openalex.org/W2397220809","doi":"https://doi.org/10.1109/icassp.2016.7471633","title":"Efficient neighborhood-based topic modeling for collaborative audio enhancement on massive crowdsourced recordings","display_name":"Efficient neighborhood-based topic modeling for collaborative audio enhancement on massive crowdsourced recordings","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2397220809","doi":"https://doi.org/10.1109/icassp.2016.7471633","mag":"2397220809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Adobe Research, University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Adobe Research, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064582903"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.7653,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85512683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"290","issue":null,"first_page":"41","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8034069538116455},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.753533124923706},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.5331107378005981},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49912595748901367},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4881201684474945},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4873707890510559},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47275716066360474},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4554852545261383},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4482845067977905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3991330862045288},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3867623209953308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34416699409484863},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.21071046590805054},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12837418913841248},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09506669640541077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034069538116455},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.753533124923706},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.5331107378005981},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49912595748901367},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4881201684474945},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4873707890510559},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47275716066360474},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4554852545261383},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4482845067977905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991330862045288},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3867623209953308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34416699409484863},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.21071046590805054},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12837418913841248},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09506669640541077},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6600000262260437,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1500571031","https://openalex.org/W1865000480","https://openalex.org/W1902027874","https://openalex.org/W2053186076","https://openalex.org/W2096458822","https://openalex.org/W2107939926","https://openalex.org/W2110990863","https://openalex.org/W2114539221","https://openalex.org/W2117150818","https://openalex.org/W2122146326","https://openalex.org/W2129227482","https://openalex.org/W2135029798","https://openalex.org/W2144750001","https://openalex.org/W2147717514","https://openalex.org/W2153894711","https://openalex.org/W2160212519","https://openalex.org/W2169698188","https://openalex.org/W2206458544","https://openalex.org/W2401258970","https://openalex.org/W3143596294","https://openalex.org/W6676099231","https://openalex.org/W6677513291","https://openalex.org/W6680012447","https://openalex.org/W6684000755","https://openalex.org/W6712867848"],"related_works":["https://openalex.org/W2009838541","https://openalex.org/W2088100285","https://openalex.org/W1590604789","https://openalex.org/W2076145524","https://openalex.org/W2743050194","https://openalex.org/W1595500397","https://openalex.org/W2088690926","https://openalex.org/W1979717040","https://openalex.org/W2155527258","https://openalex.org/W2511638641"],"abstract_inverted_index":{"Collaborative":[0],"Audio":[1],"Enhancement":[2],"(CAE)":[3],"aims":[4],"at":[5,133],"separating":[6],"a":[7,14,19,23,35,39,43,125,129,150,156,164],"dominant":[8],"source":[9,86,95],"from":[10],"crowdsourced":[11],"recordings":[12],"of":[13,31,64,67,123],"scene.":[15],"This":[16,75],"paper":[17],"proposes":[18],"CAE":[20],"setup":[21],"as":[22,85],"big":[24],"ad-hoc":[25],"microphone":[26],"array":[27,78],"problem,":[28],"assuming":[29],"hundreds":[30],"sensors":[32,58],"scattered":[33],"over":[34],"large":[36],"scene,":[37],"e.g.":[38],"concert":[40],"hall":[41],"or":[42],"street":[44],"riot.":[45],"An":[46],"important":[47],"characteristic":[48],"in":[49],"such":[50,84,124],"cases":[51],"is":[52,100],"the":[53,65,92,117,120,160,175,181,187],"fact":[54],"that":[55,174],"not":[56],"all":[57,191],"capture":[59],"useful":[60],"information,":[61],"mainly":[62],"because":[63],"existence":[66],"strong":[68],"local":[69],"noise":[70],"interferences":[71],"and":[72,119,154],"recording":[73],"artifacts.":[74],"renders":[76],"traditional":[77],"processing":[79],"techniques":[80],"inadequate":[81],"for":[82],"tasks":[83],"enhancement.":[87],"One":[88],"way":[89],"to":[90,101,147,163,180],"recover":[91],"most":[93],"common":[94],"while":[96],"suppressing":[97],"recording-specific":[98],"interference,":[99],"share":[102],"latent":[103],"components":[104],"across":[105],"simultaneous":[106],"models":[107],"on":[108,116],"multiple":[109],"magnitude":[110],"spectrograms.":[111],"The":[112],"proposed":[113,176],"method":[114],"improves":[115],"quality":[118,183],"computational":[121],"requirements":[122],"model":[126,189],"by":[127],"using":[128,166,190],"two-stage":[130],"nearest-neighborhood":[131],"search":[132,140],"every":[134],"EM":[135],"update.":[136],"Its":[137],"optional":[138],"first-round":[139],"uses":[141],"Hamming":[142],"distance":[143],"between":[144],"hashed":[145],"spectrograms":[146],"quickly":[148],"find":[149],"redundant":[151],"candidate":[152],"set,":[153],"then":[155],"subsequent":[157],"step":[158],"narrows":[159],"set":[161],"down":[162],"subset":[165],"more":[167],"appropriate":[168],"cross":[169],"entropy.":[170],"Experimental":[171],"results":[172],"show":[173],"neighborhood":[177],"schemes":[178],"converge":[179],"better":[182],"solutions":[184],"faster":[185],"than":[186],"comprehensive":[188],"data.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}