{"id":"https://openalex.org/W4319862706","doi":"https://doi.org/10.1109/slt54892.2023.10022986","title":"Flow-ER: A Flow-Based Embedding Regularization Strategy for Robust Speech Representation Learning","display_name":"Flow-ER: A Flow-Based Embedding Regularization Strategy for Robust Speech Representation Learning","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862706","doi":"https://doi.org/10.1109/slt54892.2023.10022986"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022986","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022986","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082739860","display_name":"Woo Hyun Kang","orcid":"https://orcid.org/0000-0001-8739-9349"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Woo Hyun Kang","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM)","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088749621","display_name":"Jahangir Alam","orcid":"https://orcid.org/0000-0003-4174-9862"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jahangir Alam","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM)","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066980762","display_name":"Abderrahim Fathan","orcid":"https://orcid.org/0000-0002-5749-1643"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abderrahim Fathan","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM)","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00734516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"570"},"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/embedding","display_name":"Embedding","score":0.7600331902503967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591605186462402},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6085154414176941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595746636390686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48957332968711853},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4862171709537506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4807269871234894},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46617627143859863},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46171852946281433},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4268595576286316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4110882580280304}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7600331902503967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591605186462402},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6085154414176941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595746636390686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48957332968711853},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4862171709537506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4807269871234894},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46617627143859863},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46171852946281433},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4268595576286316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4110882580280304},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022986","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022986","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G270585729","display_name":"Robust Speaker Verification in Real Application Scenarios","funder_award_id":"rgpin-2019-05381","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2046056978","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2766049740","https://openalex.org/W2803832867","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2916058012","https://openalex.org/W2916104401","https://openalex.org/W2937328535","https://openalex.org/W2962959915","https://openalex.org/W3010874390","https://openalex.org/W3013020904","https://openalex.org/W3017138616","https://openalex.org/W3024869864","https://openalex.org/W3034512278","https://openalex.org/W3036928441","https://openalex.org/W3046796449","https://openalex.org/W3090254849","https://openalex.org/W3102070904","https://openalex.org/W3127781933","https://openalex.org/W3158663310","https://openalex.org/W3166898278","https://openalex.org/W3184661981","https://openalex.org/W4212774754","https://openalex.org/W4283026792","https://openalex.org/W4293363567","https://openalex.org/W6631362777","https://openalex.org/W6766978945","https://openalex.org/W6779459370","https://openalex.org/W6790622591"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W3048601286","https://openalex.org/W2965925734"],"abstract_inverted_index":{"Over":[0],"the":[1,12,44,50,67,75,86,91,95,109,125],"recent":[2],"years,":[3],"various":[4],"deep":[5,13],"learning-based":[6,14],"embedding":[7,15,68],"methods":[8,17],"were":[9],"proposed.":[10],"Although":[11],"extraction":[16],"have":[18,71],"shown":[19],"good":[20],"performance":[21,33,107],"in":[22,129],"numerous":[23],"tasks":[24,118],"including":[25],"speaker":[26],"verification,":[27],"language":[28],"identification":[29],"and":[30,119],"anti-spoofing,":[31],"their":[32],"is":[34,98,112],"limited":[35],"when":[36],"it":[37],"comes":[38],"to":[39,43,49,55,70,121],"mismatched":[40],"conditions":[41],"due":[42],"variability":[45],"within":[46],"them":[47],"unrelated":[48],"main":[51],"task.":[52],"In":[53],"order":[54],"alleviate":[56],"this":[57],"problem,":[58],"we":[59],"propose":[60],"a":[61],"novel":[62],"training":[63,92,127],"strategy":[64,128],"that":[65],"regularizes":[66],"network":[69],"minimum":[72],"information":[73,87,97],"about":[74],"nuisance":[76],"attributes.":[77],"To":[78],"achieve":[79],"this,":[80],"our":[81],"proposed":[82,110],"method":[83,111],"directly":[84],"incorporates":[85],"bottleneck":[88],"scheme":[89],"into":[90],"process,":[93],"where":[94],"mutual":[96],"estimated":[99],"using":[100],"an":[101],"auxiliary":[102],"normalizing":[103],"flow":[104],"network.":[105],"The":[106],"of":[108],"evaluated":[113],"on":[114],"different":[115],"speech":[116],"processing":[117],"found":[120],"provide":[122],"improvement":[123],"over":[124],"standard":[126],"all":[130],"experimentations.":[131]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}