{"id":"https://openalex.org/W3210580025","doi":"https://doi.org/10.1109/asru51503.2021.9688231","title":"Speaker Conditioning of Acoustic Models Using Affine Transformation for Multi-Speaker Speech Recognition","display_name":"Speaker Conditioning of Acoustic Models Using Affine Transformation for Multi-Speaker Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3210580025","doi":"https://doi.org/10.1109/asru51503.2021.9688231","mag":"3210580025"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688231","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.00320","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112853229","display_name":"Midia Yousefi","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Midia Yousefi","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas,Richardson,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas,Richardson,Texas,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077809528","display_name":"John H. L. Hanse","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas,Richardson,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas,Richardson,Texas,USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112853229"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.1269,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36068755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994000196456909,"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/speech-recognition","display_name":"Speech recognition","score":0.7772095203399658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421225309371948},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7250761985778809},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6274343729019165},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5032772421836853},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5018415451049805},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4906734228134155},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43816882371902466},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.41695868968963623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3656993508338928},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3183351159095764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1003446877002716}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7772095203399658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421225309371948},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7250761985778809},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6274343729019165},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5032772421836853},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5018415451049805},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4906734228134155},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43816882371902466},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.41695868968963623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3656993508338928},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3183351159095764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1003446877002716},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688231","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.00320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00320","pdf_url":"https://arxiv.org/pdf/2111.00320","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3210580025","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.00320","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2111.00320","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.00320","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.00320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00320","pdf_url":"https://arxiv.org/pdf/2111.00320","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3210580025.pdf","grobid_xml":"https://content.openalex.org/works/W3210580025.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W109381481","https://openalex.org/W2035576074","https://openalex.org/W2101045344","https://openalex.org/W2144763279","https://openalex.org/W2408656838","https://openalex.org/W2601064856","https://openalex.org/W2738829388","https://openalex.org/W2794289187","https://openalex.org/W2884797218","https://openalex.org/W2889145072","https://openalex.org/W2890244912","https://openalex.org/W2890964092","https://openalex.org/W2899135636","https://openalex.org/W2900212944","https://openalex.org/W2912512634","https://openalex.org/W2939690918","https://openalex.org/W2963477857","https://openalex.org/W2963742216","https://openalex.org/W2963921132","https://openalex.org/W2966215472","https://openalex.org/W2972362771","https://openalex.org/W2973049979","https://openalex.org/W3007946293","https://openalex.org/W3008801297","https://openalex.org/W3015528371","https://openalex.org/W3015834770","https://openalex.org/W3015923889","https://openalex.org/W3016131876","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3094892544","https://openalex.org/W3096664139","https://openalex.org/W3097224945","https://openalex.org/W3097882114","https://openalex.org/W3099832538","https://openalex.org/W3109079702","https://openalex.org/W3137695714","https://openalex.org/W3162249256","https://openalex.org/W3196705474","https://openalex.org/W6740674931","https://openalex.org/W6754576867","https://openalex.org/W6761176036","https://openalex.org/W6841262374"],"related_works":["https://openalex.org/W2303753910","https://openalex.org/W2770454110","https://openalex.org/W2013786873","https://openalex.org/W2944782944","https://openalex.org/W2927063407","https://openalex.org/W3167596786","https://openalex.org/W3105928222","https://openalex.org/W1948754462","https://openalex.org/W3147252365","https://openalex.org/W2153890400","https://openalex.org/W2127534926","https://openalex.org/W2891609809","https://openalex.org/W3103434036","https://openalex.org/W2786105640","https://openalex.org/W2972867623","https://openalex.org/W3011869934","https://openalex.org/W3169874602","https://openalex.org/W2084558107","https://openalex.org/W2552555813","https://openalex.org/W3011034465"],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,20,23,27,39,48,57,65,72,108,113,150],"problem":[4],"of":[5,10,74],"single-channel":[6],"Automatic":[7],"Speech":[8],"Recognition":[9],"a":[11,84,102],"target":[12],"speaker":[13,33,54,61,80,99,115,124],"within":[14],"an":[15,119],"overlap":[16,144],"speech":[17,132,145],"scenario.":[18],"In":[19],"proposed":[21,79,114],"method,":[22],"hidden":[24],"representations":[25],"in":[26,71],"acoustic":[28,49,58,66,93,104,128,153],"model":[29,50,67,94,154],"are":[30,45],"modulated":[31],"by":[32],"auxiliary":[34,76,125],"information":[35,55,126],"to":[36,52,68,91,122,149],"recognize":[37],"only":[38],"desired":[40],"speaker.":[41],"Affine":[42],"transformation":[43],"layers":[44],"inserted":[46],"into":[47],"network":[51],"integrate":[53],"with":[56,127],"features.":[59],"The":[60,78],"conditioning":[62,81,100,116],"process":[63],"allows":[64],"perform":[69],"computation":[70],"context":[73],"target-speaker":[75],"information.":[77],"method":[82,117],"is":[83,118],"general":[85],"approach":[86],"and":[87,136,143],"can":[88],"be":[89],"applied":[90],"any":[92],"architecture.":[95],"Here,":[96],"we":[97],"employ":[98],"on":[101,107],"ResNet":[103,152],"model.":[105],"Experiments":[106],"WSJ":[109],"corpus":[110],"show":[111],"that":[112],"effective":[120],"solution":[121],"fuse":[123],"features":[129],"for":[130,141],"multi-speaker":[131],"recognition,":[133],"achieving":[134],"+9%":[135],"+20%":[137],"relative":[138],"WER":[139],"reduction":[140],"clean":[142],"scenarios,":[146],"respectively,":[147],"compared":[148],"original":[151],"baseline.":[155]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}