{"id":"https://openalex.org/W4375869100","doi":"https://doi.org/10.1109/icassp49357.2023.10095022","title":"Reverberation as Supervision For Speech Separation","display_name":"Reverberation as Supervision For Speech Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869100","doi":"https://doi.org/10.1109/icassp49357.2023.10095022"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060415215","display_name":"Rohith Aralikatti","orcid":"https://orcid.org/0000-0002-6857-6896"},"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"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohith Aralikatti","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]},{"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":["DE","US"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Paderborn University, Paderborn, Germany","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"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","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"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/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"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":"Aswin Subramanian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"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/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"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","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8389651775360107},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7073632478713989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6726301908493042},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.655049204826355},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6189075112342834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5609550476074219},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.5305840373039246},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5067227482795715},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5047661066055298},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47215983271598816},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.42493438720703125},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42184555530548096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37611502408981323},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35388338565826416},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27344250679016113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24618932604789734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22929900884628296},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13073331117630005},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09477564692497253}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8389651775360107},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7073632478713989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726301908493042},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.655049204826355},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6189075112342834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5609550476074219},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.5305840373039246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5067227482795715},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5047661066055298},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47215983271598816},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.42493438720703125},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42184555530548096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37611502408981323},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35388338565826416},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27344250679016113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24618932604789734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22929900884628296},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13073331117630005},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09477564692497253},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2888954542","https://openalex.org/W2890244912","https://openalex.org/W2892163332","https://openalex.org/W2899515918","https://openalex.org/W2933708090","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962970794","https://openalex.org/W2964237233","https://openalex.org/W2981976899","https://openalex.org/W3015191643","https://openalex.org/W3015843733","https://openalex.org/W3016232124","https://openalex.org/W3016244460","https://openalex.org/W3086154751","https://openalex.org/W3093839391","https://openalex.org/W3094831814","https://openalex.org/W3099330747","https://openalex.org/W3161540261","https://openalex.org/W3163217847","https://openalex.org/W3206116612","https://openalex.org/W4211083646","https://openalex.org/W4292969786","https://openalex.org/W6632744857","https://openalex.org/W6769511080","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2780118011","https://openalex.org/W2079152323","https://openalex.org/W2128388559","https://openalex.org/W2272518678","https://openalex.org/W2140267235","https://openalex.org/W2077498359"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"reverberation":[3],"as":[4,42,80],"supervision":[5,228],"(RAS),":[6],"a":[7,34,68,187,235],"novel":[8],"unsupervised":[9,20],"loss":[10,130],"function":[11,131],"for":[12,19],"single-channel":[13],"reverberant":[14,189],"speech":[15,190],"separation.":[16],"Prior":[17],"methods":[18,44],"separation":[21,49,191],"required":[22],"the":[23,31,46,58,73,78,84,91,95,98,108,111,117,119,135,139,142,150,154,161,167,174,179,183,195,207,221,230,240],"synthesis":[24],"of":[25,27,33,48,60,77,103,110,134,166,206,220],"mixtures":[26,28,62,208],"or":[29],"assumed":[30],"existence":[32],"teacher":[35],"model,":[36],"making":[37],"them":[38],"difficult":[39],"to":[40,71,116,138,153,173],"consider":[41],"potential":[43],"explaining":[45],"emergence":[47],"abilities":[50],"in":[51,141],"an":[52],"animal\u2019s":[53],"auditory":[54],"system.":[55],"We":[56,157],"assume":[57],"availability":[59],"two-channel":[61],"at":[63],"training":[64,199,226,232],"time,":[65],"and":[66,148],"train":[67],"neural":[69],"network":[70,120,180],"separate":[72],"sources":[74,137],"given":[75],"one":[76],"channels":[79],"input":[81],"such":[82],"that":[83,125,159],"other":[85],"channel":[86,105,144],"may":[87],"be":[88],"predicted":[89,168],"from":[90],"separated":[92,136],"sources.":[93,185],"As":[94],"relationship":[96],"between":[97],"room":[99],"impulse":[100],"responses":[101],"(RIRs)":[102],"each":[104,133],"depends":[106],"on":[107,123,194,229,239],"locations":[109],"sources,":[112,214],"which":[113],"are":[114,209],"unknown":[115],"network,":[118],"cannot":[121],"rely":[122],"learning":[124],"relationship.":[126],"Instead,":[127],"our":[128],"proposed":[129],"fits":[132],"mixture":[140,152,170],"target":[143],"via":[145],"Wiener":[146],"filtering,":[147],"compares":[149],"resulting":[151],"ground-truth":[155],"one.":[156],"show":[158],"minimizing":[160],"scale-invariant":[162],"signal-to-distortion":[163],"ratio":[164],"(SI-SDR)":[165],"right-channel":[169],"with":[171,211,227],"respect":[172],"ground":[175],"truth":[176],"implicitly":[177],"guides":[178],"towards":[181],"separating":[182],"left-channel":[184],"On":[186],"semi-supervised":[188],"task":[192],"based":[193],"WHAMR!":[196],"dataset,":[197],"using":[198],"data":[200,242],"where":[201],"just":[202],"5%":[203],"(resp.,":[204,218,245],"10%)":[205],"labeled":[210,241],"associated":[212],"isolated":[213],"we":[215],"achieve":[216],"70%":[217],"78%)":[219],"SI-SDR":[222],"improvement":[223],"obtained":[224],"when":[225],"full":[231],"set,":[233],"while":[234],"model":[236],"trained":[237],"only":[238],"obtains":[243],"43%":[244],"45%).":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}