{"id":"https://openalex.org/W2984935418","doi":"https://doi.org/10.1109/taslp.2020.3013105","title":"Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision","display_name":"Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2984935418","doi":"https://doi.org/10.1109/taslp.2020.3013105","mag":"2984935418"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3013105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3013105","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.02182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fatemeh Pishdadian","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatemeh Pishdadian","raw_affiliation_strings":["Interactive Audio Lab, Northwestern University, Evanston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Audio Lab, Northwestern University, Evanston, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gordon Wichern","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":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jonathan Le Roux","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":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8211,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91231142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8859000205993652,"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":0.8859000205993652,"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":0.08479999750852585,"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":0.008899999782443047,"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/classifier","display_name":"Classifier (UML)","score":0.704200029373169},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6035000085830688},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3504999876022339},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.3409000039100647},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.325300008058548},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.325300008058548},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3034999966621399}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460000276565552},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5534999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3013105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3013105","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1911.02182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.02182","pdf_url":"https://arxiv.org/pdf/1911.02182","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.02182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.02182","pdf_url":"https://arxiv.org/pdf/1911.02182","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1946152311","https://openalex.org/W2038484192","https://openalex.org/W2046869671","https://openalex.org/W2060822897","https://openalex.org/W2094461119","https://openalex.org/W2127851351","https://openalex.org/W2153331367","https://openalex.org/W2170599041","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2354870669","https://openalex.org/W2552071709","https://openalex.org/W2575145750","https://openalex.org/W2591013610","https://openalex.org/W2654517624","https://openalex.org/W2669032454","https://openalex.org/W2734774145","https://openalex.org/W2798158991","https://openalex.org/W2799258971","https://openalex.org/W2889404825","https://openalex.org/W2891405874","https://openalex.org/W2894785362","https://openalex.org/W2898963093","https://openalex.org/W2903718461","https://openalex.org/W2938440247","https://openalex.org/W2941505948","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962753171","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/W2964159544","https://openalex.org/W2964229681","https://openalex.org/W2972411915","https://openalex.org/W2972541922","https://openalex.org/W2988200020","https://openalex.org/W2997981428","https://openalex.org/W2998490864","https://openalex.org/W2998657200","https://openalex.org/W3016038135","https://openalex.org/W6675574810","https://openalex.org/W6677053740","https://openalex.org/W6680873201","https://openalex.org/W6691781196","https://openalex.org/W6702387769","https://openalex.org/W6745117180","https://openalex.org/W6756597712","https://openalex.org/W6766320909"],"related_works":[],"abstract_inverted_index":{"While":[0],"there":[1],"has":[2,105],"been":[3],"much":[4],"recent":[5],"progress":[6],"using":[7,154,244,282],"deep":[8],"learning":[9],"techniques":[10],"to":[11,37,50,98,107,121,166,194,203,209,213,219,234,269,278],"separate":[12],"speech":[13],"and":[14,61,95,174,216,260],"music":[15,274],"audio":[16,33,118,137],"signals,":[17],"these":[18],"systems":[19],"typically":[20],"require":[21],"large":[22],"collections":[23],"of":[24,132,151,162,241,247,254],"isolated":[25,52,93,283],"sources":[26,113,231],"during":[27],"the":[28,108,128,163,168,171,175,183,192,200,210,229,235,239,263],"training":[29,66,279],"process.":[30],"When":[31],"extending":[32],"source":[34,68,197,215,275],"separation":[35,69,173],"algorithms":[36],"more":[38],"general":[39],"domains":[40],"such":[41,88,198,272],"as":[42,89,159,273],"environmental":[43],"monitoring,":[44],"it":[45,204],"may":[46],"not":[47],"be":[48,267],"possible":[49],"obtain":[51],"signals":[53],"for":[54,148],"training.":[55],"Here,":[56],"we":[57],"propose":[58],"objective":[59,189,224],"functions":[60],"network":[62,281],"architectures":[63],"that":[64,125,143,199,214,228,262],"enable":[65],"a":[67,141,145,155,196,252,280],"system":[70],"with":[71,83,298],"weak":[72,77,100,123,178],"labels.":[73],"In":[74],"this":[75],"scenario,":[76],"labels":[78,87,101,124,179],"are":[79,114],"defined":[80],"in":[81,116,134,257,296],"contrast":[82],"strong":[84],"time-frequency":[85],"(TF)":[86],"those":[90],"obtained":[91],"from":[92,251],"sources,":[94,284],"refer":[96],"either":[97],"frame-level":[99],"where":[102],"one":[103],"only":[104,126,180],"access":[106],"time":[109],"periods":[110],"when":[111],"different":[112],"active":[115],"an":[117,135,160],"mixture,":[119],"or":[120,130,185],"clip-level":[122],"indicate":[127],"presence":[129],"absence":[131],"sounds":[133,255],"entire":[136],"clip.":[138],"We":[139,237],"train":[140],"separator":[142,193],"estimates":[144],"TF":[146],"mask":[147],"each":[149],"type":[150],"sound":[152,156,300],"event,":[153],"event":[157,301],"classifier":[158,201],"assessor":[161],"separator's":[164],"performance":[165,240],"bridge":[167],"gap":[169],"between":[170],"TF-level":[172],"ground":[176],"truth":[177],"available":[181],"at":[182],"frame":[184],"clip":[186],"level.":[187],"Our":[188],"function":[190,225],"requires":[191],"estimate":[195],"applied":[202,268],"will":[205],"assign":[206],"high":[207],"probability":[208,218],"class":[211],"corresponding":[212],"low":[217],"all":[220],"other":[221,270],"classes.":[222],"The":[223],"also":[226,266],"enforces":[227],"separated":[230],"sum":[232],"up":[233],"mixture.":[236],"benchmark":[238],"our":[242,285],"algorithm":[243],"synthetic":[245],"mixtures":[246],"overlapping":[248],"events":[249],"created":[250],"database":[253],"recorded":[256],"urban":[258],"environments,":[259],"show":[261],"method":[264],"can":[265],"tasks":[271],"separation.":[276],"Compared":[277],"model":[286],"achieves":[287],"somewhat":[288],"lower":[289],"but":[290],"still":[291],"significant":[292,299],"SI-SDR":[293],"improvement,":[294],"even":[295],"scenarios":[297],"overlap.":[302]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-11-22T00:00:00"}