{"id":"https://openalex.org/W3206116612","doi":"https://doi.org/10.1109/icassp43922.2022.9747855","title":"Adapting Speech Separation to Real-World Meetings using Mixture Invariant Training","display_name":"Adapting Speech Separation to Real-World Meetings using Mixture Invariant Training","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206116612","doi":"https://doi.org/10.1109/icassp43922.2022.9747855","mag":"3206116612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747855","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5085011950","display_name":"Aswin Sivaraman","orcid":"https://orcid.org/0000-0003-2248-4846"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Sivaraman","raw_affiliation_strings":["Google Research","Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"686","last_page":"690"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7876290082931519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5694572925567627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5694470405578613},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5500662326812744},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5439720749855042},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4811921715736389},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.47184398770332336},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47130048274993896},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4546412229537964},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4399252235889435},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43559014797210693},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.43502235412597656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4010624885559082},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.124948650598526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876290082931519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5694572925567627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5694470405578613},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5500662326812744},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5439720749855042},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4811921715736389},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.47184398770332336},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47130048274993896},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4546412229537964},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4399252235889435},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43559014797210693},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.43502235412597656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4010624885559082},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.124948650598526},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747855","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1790748249","https://openalex.org/W1989314204","https://openalex.org/W2125336414","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2460742184","https://openalex.org/W2593116425","https://openalex.org/W2899626081","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W2998490864","https://openalex.org/W2998657200","https://openalex.org/W3027008958","https://openalex.org/W3093839391","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3100954996","https://openalex.org/W3151596526","https://openalex.org/W3168140565","https://openalex.org/W3197227964","https://openalex.org/W4206634335","https://openalex.org/W6631190155","https://openalex.org/W6637992904","https://openalex.org/W6678799340","https://openalex.org/W6718827390","https://openalex.org/W6756074816","https://openalex.org/W6777776875","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W2531741693","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271","https://openalex.org/W1972167985","https://openalex.org/W2350644419"],"abstract_inverted_index":{"The":[0,50],"recently-proposed":[1],"mixture":[2],"invariant":[3],"training":[4,11],"(MixIT)":[5],"is":[6],"an":[7],"unsupervised":[8,148],"method":[9],"for":[10],"single-channel":[12],"sound":[13],"separation":[14,35],"models":[15,51,136],"because":[16],"it":[17],"does":[18],"not":[19],"require":[20],"ground-truth":[21],"isolated":[22],"reference":[23,100],"sources.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,73,87,103,110],"investigate":[29],"using":[30],"MixIT":[31,151],"to":[32,97],"adapt":[33],"a":[34,76,90,113],"model":[36,116,153],"on":[37,54,84,138,155],"real":[38,55,85,131],"far-field":[39],"overlapping":[40,59],"reverberant":[41],"and":[42,61,124,130],"noisy":[43],"speech":[44,159],"data":[45],"from":[46],"the":[47,93,118],"AMI":[48,56,78],"Corpus.":[49],"are":[52,62],"tested":[53],"recordings":[57],"containing":[58],"speech,":[60],"evaluated":[63],"subjectively":[64],"by":[65],"human":[66,82,125],"listeners.":[67],"To":[68],"objectively":[69],"evaluate":[70],"our":[71],"models,":[72],"also":[74,88],"devise":[75],"synthetic":[77,129],"test":[79],"set.":[80],"For":[81],"evaluations":[83],"recordings,":[86],"propose":[89],"modification":[91],"of":[92,140],"standard":[94],"MUSHRA":[95],"protocol":[96],"handle":[98],"imperfect":[99],"signals,":[101],"which":[102],"call":[104],"MUSHIRA.":[105],"Holding":[106],"network":[107],"architectures":[108],"constant,":[109],"find":[111],"that":[112,147],"fine-tuned":[114],"semi-supervised":[115],"yields":[117],"largest":[119],"SI-SNR":[120],"improvement,":[121],"PESQ":[122],"scores,":[123],"listening":[126],"ratings":[127],"across":[128],"datasets,":[132],"outperforming":[133],"unadapted":[134],"generalist":[135],"trained":[137],"orders":[139],"magnitude":[141],"more":[142],"data.":[143],"Our":[144],"results":[145],"show":[146],"learning":[149],"through":[150],"enables":[152],"adaptation":[154],"real-world":[156],"unlabeled":[157],"spontaneous":[158],"recordings.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}