{"id":"https://openalex.org/W4406461305","doi":"https://doi.org/10.1109/slt61566.2024.10832307","title":"Combining TF-GridNet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription","display_name":"Combining TF-GridNet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461305","doi":"https://doi.org/10.1109/slt61566.2024.10832307"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5055945494","display_name":"Peter Vieting","orcid":"https://orcid.org/0000-0002-3582-5382"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Vieting","raw_affiliation_strings":["RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028362932","display_name":"Simon Berger","orcid":"https://orcid.org/0000-0003-1333-4029"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Berger","raw_affiliation_strings":["RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015424386","display_name":"Thilo von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thilo von Neumann","raw_affiliation_strings":["Paderborn University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University,Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University,Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University,Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68463515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.6622318029403687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6270713806152344},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5560641288757324},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5495520830154419},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4211946725845337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34691673517227173},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10608619451522827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07200115919113159},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.058595865964889526}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6622318029403687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270713806152344},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5560641288757324},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5495520830154419},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4211946725845337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34691673517227173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10608619451522827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07200115919113159},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.058595865964889526},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W1494198834","https://openalex.org/W1951971685","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2738829388","https://openalex.org/W2799923439","https://openalex.org/W2889503488","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2982456909","https://openalex.org/W3016232124","https://openalex.org/W3094831814","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3099832538","https://openalex.org/W3103005696","https://openalex.org/W3105532142","https://openalex.org/W3185109982","https://openalex.org/W3207834622","https://openalex.org/W3209984917","https://openalex.org/W3210390090","https://openalex.org/W3213661887","https://openalex.org/W4226491018","https://openalex.org/W4297841603","https://openalex.org/W4312666663","https://openalex.org/W4372271367","https://openalex.org/W4372346876","https://openalex.org/W4385756463","https://openalex.org/W4385822816","https://openalex.org/W4390660238","https://openalex.org/W4401609245","https://openalex.org/W6757717501","https://openalex.org/W6769802879"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Many":[0],"real-life":[1],"applications":[2],"of":[3,10,57,82,87,99,133],"automatic":[4],"speech":[5,20,36,52],"recognition":[6],"(ASR)":[7],"require":[8],"processing":[9],"overlapped":[11],"speech.":[12],"A":[13],"common":[14],"method":[15],"involves":[16],"first":[17],"separating":[18],"the":[19,50,55,65,95,124,139],"into":[21],"overlap-free":[22],"streams":[23],"on":[24,112],"which":[25],"ASR":[26],"is":[27],"performed.":[28],"Recently,":[29],"TF-GridNet":[30,121],"has":[31],"shown":[32],"impressive":[33],"performance":[34,111],"in":[35,38,107],"separation":[37,58,131],"real":[39],"reverberant":[40],"conditions.":[41],"Furthermore,":[42],"a":[43,69,74,108,115],"mixture":[44,66,134],"encoder":[45,67],"was":[46],"proposed":[47],"that":[48,120],"leverages":[49],"mixed":[51],"to":[53,73],"mitigate":[54],"effect":[56],"artifacts.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"extended":[64],"from":[68],"static":[70],"two-speaker":[71],"scenario":[72],"natural":[75],"meeting":[76],"context":[77],"featuring":[78],"an":[79],"arbitrary":[80],"number":[81],"speakers":[83],"and":[84,129],"varying":[85,100],"degrees":[86],"overlap.":[88],"We":[89,136],"further":[90,137],"demonstrate":[91],"its":[92],"limits":[93],"by":[94],"integration":[96],"with":[97],"separators":[98],"strength":[101],"including":[102],"TF-GridNet.":[103],"Our":[104],"experiments":[105],"result":[106],"new":[109],"state-of-the-art":[110],"LibriCSS":[113],"using":[114],"single":[116],"microphone.":[117],"They":[118],"show":[119],"largely":[122],"closes":[123],"gap":[125],"between":[126],"previous":[127],"methods":[128],"oracle":[130],"independent":[132],"encoding.":[135],"investigate":[138],"remaining":[140],"potential":[141],"for":[142],"improvement.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}