{"id":"https://openalex.org/W2943934118","doi":"https://doi.org/10.21437/interspeech.2019-1728","title":"Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech","display_name":"Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2943934118","doi":"https://doi.org/10.21437/interspeech.2019-1728","mag":"2943934118"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1728","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.03500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074570151","display_name":"Tobias Menne","orcid":"https://orcid.org/0000-0002-3289-2344"},"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":true,"raw_author_name":"Tobias Menne","raw_affiliation_strings":["AppTek GmbH, 52062 Aachen, Germany","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH, 52062 Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064043969","display_name":"Ilya Sklyar","orcid":null},"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":"Ilya Sklyar","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"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":["Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"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":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany","AppTek GmbH, 52062 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, 52062 Aachen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074570151"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":4.1742,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94966525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2638","last_page":"2642"},"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":0.9998999834060669,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8410356044769287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7707638740539551},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6559658050537109},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.652268648147583},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5858265161514282},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.529192328453064},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4817247688770294},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.48134884238243103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46998775005340576},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4148465394973755},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39678606390953064},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3816855847835541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410356044769287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7707638740539551},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6559658050537109},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.652268648147583},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5858265161514282},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.529192328453064},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4817247688770294},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.48134884238243103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46998775005340576},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4148465394973755},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39678606390953064},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3816855847835541},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1728","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.03500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03500","pdf_url":"https://arxiv.org/pdf/1905.03500","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.03500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03500","pdf_url":"https://arxiv.org/pdf/1905.03500","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":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2024200390","https://openalex.org/W2101045344","https://openalex.org/W2125336414","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2782451907","https://openalex.org/W2801839390","https://openalex.org/W2884797218","https://openalex.org/W2890244912","https://openalex.org/W2916979304","https://openalex.org/W2949117887","https://openalex.org/W2962715207","https://openalex.org/W2962728618","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W151018310","https://openalex.org/W2620660273","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W4385611764","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Significant":[0],"performance":[1,64],"degradation":[2],"of":[3,18,27,51,71,83,104,110,115,123,136,160,166],"automatic":[4],"speech":[5,82,106,114,158,172],"recognition":[6],"(ASR)":[7],"systems":[8],"is":[9,30,61,173],"observed":[10],"when":[11],"the":[12,19,25,31,55,62,69,81,89,98,111,152,179],"audio":[13,99],"signal":[14,100,112],"contains":[15,77,101,113],"cross-talk.":[16],"One":[17],"recently":[20],"proposed":[21],"approaches":[22],"to":[23,68,151,169],"solve":[24],"problem":[26],"multi-speaker":[28],"ASR":[29,96,131,188],"deep":[32],"clustering":[33],"(DPCL)":[34],"approach.":[35],"Combining":[36],"DPCL":[37,125,168],"with":[38],"a":[39,46,93,127,134,145],"state-of-the-art":[40],"hybrid":[41],"acoustic":[42],"model,":[43],"we":[44,143],"obtain":[45],"word":[47],"error":[48],"rate":[49],"(WER)":[50],"16.5":[52],"%":[53],"on":[54],"commonly":[56],"used":[57],"wsj0-2mix":[58,75,153,184],"dataset,":[59,154],"which":[60],"best":[63,70],"reported":[65],"thus":[66],"far":[67],"our":[72],"knowledge.":[73],"The":[74,164],"dataset":[76],"simulated":[78],"cross-talk":[79],"where":[80],"multiple":[84,116],"speakers":[85],"overlaps":[86],"for":[87,130],"almost":[88],"entire":[90],"utterance.":[91],"In":[92],"more":[94,186],"realistic":[95,187],"scenario":[97,135],"significant":[102],"portions":[103],"single-speaker":[105],"and":[107,185],"only":[108],"part":[109],"competing":[117],"speakers.":[118],"This":[119],"paper":[120],"investigates":[121],"obstacles":[122],"applying":[124,167],"as":[126,191],"preprocessing":[128],"method":[129],"in":[132],"such":[133,190],"sparsely":[137,156,170],"overlapping":[138,157,171,181],"speech.":[139],"To":[140],"this":[141],"end":[142],"present":[144],"data":[146],"simulation":[147],"approach,":[148],"closely":[149],"related":[150],"generating":[155],"datasets":[159,182],"arbitrary":[161],"overlap":[162],"ratio.":[163],"analysis":[165],"an":[174],"important":[175],"interim":[176],"step":[177],"between":[178],"fully":[180],"like":[183],"datasets,":[189],"CHiME-5":[192],"or":[193],"AMI.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}