{"id":"https://openalex.org/W4372346845","doi":"https://doi.org/10.1109/icassp49357.2023.10096722","title":"Enhancing and Adversarial: Improve ASR with Speaker Labels","display_name":"Enhancing and Adversarial: Improve ASR with Speaker Labels","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346845","doi":"https://doi.org/10.1109/icassp49357.2023.10096722"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100636970","display_name":"Wei Zhou","orcid":"https://orcid.org/0009-0006-3754-8872"},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]},{"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":"Wei Zhou","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020369346","display_name":"Haotian Wu","orcid":"https://orcid.org/0000-0003-0597-4835"},"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":"Haotian Wu","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419466","display_name":"Jingjing Xu","orcid":"https://orcid.org/0000-0002-5763-8369"},"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":"Jingjing Xu","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060987315","display_name":"Mohammad Zeineldeen","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"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohammad Zeineldeen","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060461441","display_name":"Christoph L\u00fcscher","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"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph L\u00fcscher","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"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"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"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"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100636970"],"corresponding_institution_ids":["https://openalex.org/I887968799","https://openalex.org/I99977706"],"apc_list":null,"apc_paid":null,"fwci":1.049,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80545143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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":0.9966999888420105,"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/adversarial-system","display_name":"Adversarial system","score":0.8447877168655396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.762337863445282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.706843376159668},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4947032630443573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197281002998352},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38012102246284485}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8447877168655396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762337863445282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.706843376159668},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4947032630443573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197281002998352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38012102246284485}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1731081199","https://openalex.org/W2009150118","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2166637769","https://openalex.org/W2510867321","https://openalex.org/W2584667682","https://openalex.org/W2769025471","https://openalex.org/W2796339975","https://openalex.org/W2889494795","https://openalex.org/W2962684181","https://openalex.org/W2962995362","https://openalex.org/W2963266252","https://openalex.org/W2963351448","https://openalex.org/W2964099675","https://openalex.org/W2972692349","https://openalex.org/W2973094925","https://openalex.org/W3035431747","https://openalex.org/W3097777922","https://openalex.org/W3106526813","https://openalex.org/W3197285286","https://openalex.org/W3203140070","https://openalex.org/W4224518768","https://openalex.org/W4296069265","https://openalex.org/W4297841407","https://openalex.org/W4297841520","https://openalex.org/W6637618735","https://openalex.org/W6725448924","https://openalex.org/W6732862412","https://openalex.org/W6745831770"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"ASR":[0,83,138],"can":[1],"be":[2],"improved":[3],"by":[4],"multi-task":[5],"learning":[6],"(MTL)":[7],"with":[8,20,44],"domain":[9,12,25],"enhancing":[10,90],"or":[11],"adversarial":[13,64,92,109],"training,":[14],"which":[15],"are":[16,74],"two":[17,41],"opposite":[18,42],"objectives":[19,43],"the":[21,78,82,103,120,127],"aim":[22],"to":[23,37,47,76,87],"increase/decrease":[24],"variance":[26],"towards":[27],"domain-aware/agnostic":[28],"ASR,":[29],"respectively.":[30],"In":[31],"this":[32],"work,":[33],"we":[34],"study":[35],"how":[36],"best":[38,112],"apply":[39,88],"these":[40],"speaker":[45,89],"labels":[46],"improve":[48],"conformer-based":[49],"ASR.":[50],"We":[51,94,124],"also":[52,95,125],"propose":[53],"a":[54],"novel":[55],"adaptive":[56],"gradient":[57],"reversal":[58],"layer":[59],"for":[60,99],"stable":[61],"and":[62,71,91,136],"effective":[63],"training":[65],"without":[66],"tuning":[67],"effort.":[68],"Detailed":[69],"analysis":[70],"experimental":[72],"verification":[73],"conducted":[75],"show":[77],"optimal":[79],"positions":[80],"in":[81],"neural":[84],"network":[85],"(NN)":[86],"training.":[93,110],"explore":[96],"their":[97],"combination":[98],"further":[100],"improvement,":[101],"achieving":[102],"same":[104],"performance":[105],"as":[106],"i-vectors":[107],"plus":[108],"Our":[111],"speaker-based":[113,131],"MTL":[114,132],"achieves":[115],"7%":[116],"relative":[117],"improvement":[118],"on":[119],"Switchboard":[121],"Hub5\u201900":[122],"set.":[123],"investigate":[126],"effect":[128],"of":[129],"such":[130],"w.r.t.":[133],"cleaner":[134],"dataset":[135],"weaker":[137],"NN.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}