{"id":"https://openalex.org/W2981498029","doi":"https://doi.org/10.23919/eusipco47968.2020.9287541","title":"Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition","display_name":"Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W2981498029","doi":"https://doi.org/10.23919/eusipco47968.2020.9287541","mag":"2981498029"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287541","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/1910.11114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113968312","display_name":"Sunit Sivasankaran","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sunit Sivasankaran","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","Universit\u00e9 de Lorraine,CNRS, INRIA, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine,CNRS, INRIA, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1326498283","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Emmanuel Vincent","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","Universit\u00e9 de Lorraine,CNRS, INRIA, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine,CNRS, INRIA, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1326498283","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Fohr","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","Universit\u00e9 de Lorraine,CNRS, INRIA, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine,CNRS, INRIA, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1326498283","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00665319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"350"},"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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/speech-recognition","display_name":"Speech recognition","score":0.7692407369613647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6778864860534668},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6629006862640381},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5790810585021973},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5608359575271606},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4911942183971405},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.44405287504196167},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.42096057534217834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39650189876556396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3208865523338318},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11518263816833496},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.07307785749435425}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7692407369613647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6778864860534668},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6629006862640381},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5790810585021973},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5608359575271606},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4911942183971405},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.44405287504196167},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.42096057534217834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39650189876556396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3208865523338318},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11518263816833496},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.07307785749435425},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287541","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11114","pdf_url":"https://arxiv.org/pdf/1910.11114","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"},{"id":"mag:2981498029","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.11114","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":"pmh:oai:HAL:hal-02355669v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02355669","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-02355669","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-02355669v3","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02355669","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://eusipco2020.org/","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1910.11114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11114","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11114","pdf_url":"https://arxiv.org/pdf/1910.11114","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G3872131408","display_name":"Robust voice command adapted to the user and to the context for AAL","funder_award_id":"ANR-16-CE33-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2039553327","https://openalex.org/W2044222806","https://openalex.org/W2046317813","https://openalex.org/W2158143227","https://openalex.org/W2221409856","https://openalex.org/W2330074731","https://openalex.org/W2514741789","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2747306262","https://openalex.org/W2786625961","https://openalex.org/W2884797218","https://openalex.org/W2889061314","https://openalex.org/W2891054259","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W2943934118","https://openalex.org/W2963301902","https://openalex.org/W2963488660","https://openalex.org/W2972449503","https://openalex.org/W4206633762","https://openalex.org/W4249052411","https://openalex.org/W6702482642","https://openalex.org/W6754904195"],"related_works":["https://openalex.org/W3043433769","https://openalex.org/W3092366533","https://openalex.org/W3016094953","https://openalex.org/W3015944949","https://openalex.org/W1520071769","https://openalex.org/W2564013664","https://openalex.org/W2100823947","https://openalex.org/W2104654244","https://openalex.org/W3145387657","https://openalex.org/W2067115593","https://openalex.org/W2285729352","https://openalex.org/W2611351721","https://openalex.org/W1583792410","https://openalex.org/W2125989302","https://openalex.org/W3103003256","https://openalex.org/W3025547567","https://openalex.org/W280592816","https://openalex.org/W2163217414","https://openalex.org/W236686179","https://openalex.org/W1588020612"],"abstract_inverted_index":{"We":[0,89],"investigate":[1],"the":[2,8,20,32,44,48,62,75,86,99,105,108,114,127,135,147,154,169],"effect":[3],"of":[4,10,107,113,122],"speaker":[5,21,49,64],"localization":[6,130,136],"on":[7],"performance":[9,106],"speech":[11,24,155],"recognition":[12],"systems":[13],"in":[14,28,85,111,174],"a":[15,35,57,66,91],"multispeaker,":[16,93],"multichannel":[17],"environment.":[18],"Given":[19],"location":[22,50],"information,":[23],"separation":[25,156],"is":[26,40,52,71],"performed":[27],"three":[29],"stages.":[30],"In":[31],"first":[33],"stage,":[34],"simple":[36],"delay-and-sum":[37],"(DS)":[38],"beamformer":[39,84],"used":[41,54,72],"to":[42,55,61,73,80,151],"enhance":[43],"signal":[45],"impinging":[46],"from":[47,98],"which":[51],"then":[53],"estimate":[56],"time-frequency":[58],"mask":[59,70],"corresponding":[60],"localized":[63],"using":[65,126,134],"neural":[67],"network.":[68],"This":[69],"compute":[74],"second":[76],"order":[77],"statistics":[78],"and":[79,103,132],"derive":[81],"an":[82],"adaptive":[83],"third":[87],"stage.":[88],"generated":[90],"multichannel,":[92],"reverberated,":[94],"noisy":[95],"dataset":[96],"inspired":[97],"well":[100,172],"studied":[101],"WSJ0-2mix":[102],"study":[104],"proposed":[109],"pipeline":[110],"terms":[112],"word":[115],"error":[116],"rate":[117],"(WER).":[118],"An":[119],"average":[120],"WER":[121],"29.4%":[123],"was":[124,149],"achieved":[125],"ground":[128],"truth":[129],"information":[131,137],"42.4%":[133],"estimated":[138],"via":[139],"GCC-PHAT.":[140],"Though":[141],"higher":[142],"signal-to-interference":[143],"ratio":[144],"(SIR)":[145],"between":[146],"speakers":[148,170],"found":[150],"positively":[152],"impact":[153],"performance,":[157],"equivalent":[158],"performances":[159],"were":[160],"obtained":[161],"for":[162],"mixtures":[163],"with":[164],"lower":[165],"SIR":[166],"values":[167],"when":[168],"are":[171],"separated":[173],"space.":[175]},"counts_by_year":[],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2022-07-28T00:00:00"}
