{"id":"https://openalex.org/W3016038135","doi":"https://doi.org/10.1109/icassp40776.2020.9053055","title":"Learning to Separate Sounds from Weakly Labeled Scenes","display_name":"Learning to Separate Sounds from Weakly Labeled Scenes","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016038135","doi":"https://doi.org/10.1109/icassp40776.2020.9053055","mag":"3016038135"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5072149059","display_name":"Fatemeh Pishdadian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fatemeh Pishdadian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072149059"],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":1.3638,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80796577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"95"},"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":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8469690680503845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7487138509750366},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7210023403167725},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6751095652580261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5250413417816162},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.501760721206665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4743936061859131},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4604654014110565}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8469690680503845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487138509750366},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7210023403167725},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6751095652580261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250413417816162},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.501760721206665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4743936061859131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4604654014110565},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2038484192","https://openalex.org/W2127851351","https://openalex.org/W2153331367","https://openalex.org/W2221409856","https://openalex.org/W2253434170","https://openalex.org/W2331166300","https://openalex.org/W2354870669","https://openalex.org/W2552071709","https://openalex.org/W2654517624","https://openalex.org/W2734774145","https://openalex.org/W2799258971","https://openalex.org/W2903137797","https://openalex.org/W2903718461","https://openalex.org/W2938440247","https://openalex.org/W2941505948","https://openalex.org/W2962866211","https://openalex.org/W2963406748","https://openalex.org/W2963610932","https://openalex.org/W2963723765","https://openalex.org/W2963751183","https://openalex.org/W2963933499","https://openalex.org/W2964058413","https://openalex.org/W2964159544","https://openalex.org/W2964229681","https://openalex.org/W2972411915","https://openalex.org/W2988200020","https://openalex.org/W2997981428","https://openalex.org/W2998490864","https://openalex.org/W2998657200","https://openalex.org/W3103314642","https://openalex.org/W3123940584","https://openalex.org/W6691781196","https://openalex.org/W6702387769","https://openalex.org/W6746448976","https://openalex.org/W6750683188","https://openalex.org/W6752109149","https://openalex.org/W6756597712","https://openalex.org/W6761464603","https://openalex.org/W6767612388","https://openalex.org/W6772029211","https://openalex.org/W6788837655"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1974981856","https://openalex.org/W1983045063","https://openalex.org/W2401567014","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W178436704","https://openalex.org/W3150394233"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"for":[3,76,106,115],"monaural":[4],"audio":[5],"source":[6,39,101,112],"separation":[7,40],"are":[8,62],"typically":[9],"trained":[10],"on":[11,149],"large":[12],"collections":[13],"of":[14,79,138],"isolated":[15,153],"sources,":[16,154],"which":[17],"may":[18],"not":[19],"be":[20],"available":[21],"in":[22,64,143],"domains":[23],"such":[24],"as":[25],"environmental":[26],"monitoring.":[27],"We":[28,67,132],"propose":[29],"objective":[30,92,120],"functions":[31],"and":[32,113,151],"network":[33],"architectures":[34],"that":[35,71,111,124],"enable":[36],"training":[37,148],"a":[38,69,73,83,99],"system":[41],"with":[42,47],"weak":[43,52,104],"labels.":[44],"In":[45],"contrast":[46],"strong":[48],"time-frequency":[49],"(TF)":[50],"labels,":[51],"labels":[53,105],"only":[54],"indicate":[55],"the":[56,95,107,125,130],"time":[57],"periods":[58],"where":[59],"different":[60],"sources":[61,127],"active":[63],"this":[65],"scenario.":[66],"train":[68],"separator":[70],"outputs":[72],"TF":[74],"mask":[75],"each":[77],"type":[78],"sound":[80,140],"event,":[81],"using":[82,135],"classifier":[84,96],"to":[85,98,102,110,129,147],"pool":[86],"label":[87],"estimates":[88],"across":[89],"frequency.":[90],"Our":[91],"function":[93,121],"requires":[94],"applied":[97],"separated":[100,126],"output":[103],"class":[108],"corresponding":[109],"zeros":[114],"all":[116],"other":[117],"classes.":[118],"The":[119],"also":[122],"enforces":[123],"sum":[128],"mixture.":[131],"benchmark":[133],"performance":[134],"synthetic":[136],"mixtures":[137,150],"overlapping":[139],"events":[141],"recorded":[142],"urban":[144],"environments.":[145],"Compared":[146],"their":[152],"our":[155],"model":[156],"still":[157],"achieves":[158],"significant":[159],"SDR":[160],"improvement.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}