{"id":"https://openalex.org/W4221153054","doi":"https://doi.org/10.1109/icassp43922.2022.9747185","title":"Learnable Nonlinear Compression for Robust Speaker Verification","display_name":"Learnable Nonlinear Compression for Robust Speaker Verification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221153054","doi":"https://doi.org/10.1109/icassp43922.2022.9747185"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747185","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.05236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014303571","display_name":"Xuechen Liu","orcid":"https://orcid.org/0000-0003-1207-5651"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Xuechen Liu","raw_affiliation_strings":["University of Eastern Finland,School of Computing,Joensuu,Finland","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","University of Eastern Finland ( Educa, Tulliportinkatu 1, 80130 Joensuu, Finland - Finland)"],"affiliations":[{"raw_affiliation_string":"University of Eastern Finland,School of Computing,Joensuu,Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]},{"raw_affiliation_string":"University of Eastern Finland ( Educa, Tulliportinkatu 1, 80130 Joensuu, Finland - Finland)","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"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/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":"Md Sahidullah","raw_affiliation_strings":["Universit&#x00E9; de Lorraine,CNRS, Inria, LORIA,Nancy,France,F-54000","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Lorraine,CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["University of Eastern Finland,School of Computing,Joensuu,Finland","University of Eastern Finland ( Educa, Tulliportinkatu 1, 80130 Joensuu, Finland - Finland)"],"affiliations":[{"raw_affiliation_string":"University of Eastern Finland,School of Computing,Joensuu,Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland ( Educa, Tulliportinkatu 1, 80130 Joensuu, Finland - Finland)","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014303571"],"corresponding_institution_ids":["https://openalex.org/I175532246"],"apc_list":null,"apc_paid":null,"fwci":0.313,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47859036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7962","last_page":"7966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9955000281333923,"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/robustness","display_name":"Robustness (evolution)","score":0.7909153699874878},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6845216751098633},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6486969590187073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.640535295009613},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5564916133880615},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4877263009548187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4395981431007385},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42711061239242554},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.42437028884887695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3011745512485504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23300683498382568},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.20030993223190308}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7909153699874878},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6845216751098633},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6486969590187073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.640535295009613},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5564916133880615},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4877263009548187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4395981431007385},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42711061239242554},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.42437028884887695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3011745512485504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23300683498382568},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.20030993223190308},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747185","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.05236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.05236","pdf_url":"https://arxiv.org/pdf/2202.05236","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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-03616852v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-03616852","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. &#x27E8;10.1109/ICASSP43922.2022.9747185&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.05236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.05236","pdf_url":"https://arxiv.org/pdf/2202.05236","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W172888084","https://openalex.org/W617047264","https://openalex.org/W1589137271","https://openalex.org/W1687555731","https://openalex.org/W1936725236","https://openalex.org/W2028124797","https://openalex.org/W2072473772","https://openalex.org/W2114719288","https://openalex.org/W2119125873","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2326699523","https://openalex.org/W2726515241","https://openalex.org/W2746321128","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2899201823","https://openalex.org/W2916104401","https://openalex.org/W2928556070","https://openalex.org/W2938358845","https://openalex.org/W2962901777","https://openalex.org/W2963881567","https://openalex.org/W2964052309","https://openalex.org/W2972425344","https://openalex.org/W2972909277","https://openalex.org/W2973053574","https://openalex.org/W2991951409","https://openalex.org/W3004720752","https://openalex.org/W3015289235","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3089353926","https://openalex.org/W3094735979","https://openalex.org/W3103152812","https://openalex.org/W3104056985","https://openalex.org/W3129570578","https://openalex.org/W3137249133","https://openalex.org/W3160743249","https://openalex.org/W3161158930","https://openalex.org/W3161792602","https://openalex.org/W3179102351","https://openalex.org/W3202106304","https://openalex.org/W4206519171","https://openalex.org/W4236328885","https://openalex.org/W6635152626","https://openalex.org/W6771538394","https://openalex.org/W6784275183","https://openalex.org/W6784933028"],"related_works":["https://openalex.org/W2104490101","https://openalex.org/W3030709726","https://openalex.org/W2966487450","https://openalex.org/W2612632602","https://openalex.org/W2321805087","https://openalex.org/W624280404","https://openalex.org/W2207317090","https://openalex.org/W4200153455","https://openalex.org/W4389543013","https://openalex.org/W4322614724"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"focus":[4],"on":[5,16,39,53,60,85,93,99],"nonlinear":[6,27],"compression":[7,28,45,70],"methods":[8,29,36,71],"in":[9,31],"spectral":[10],"features":[11],"for":[12,82],"speaker":[13],"verification":[14],"based":[15,38,84],"deep":[17],"neural":[18],"network.":[19],"We":[20,47],"consider":[21],"different":[22],"kinds":[23],"of":[24,109],"channel-dependent":[25],"(CD)":[26],"optimized":[30],"a":[32,102],"data-driven":[33],"manner.":[34],"Our":[35],"are":[37],"power":[40,86],"nonlinearities":[41],"and":[42,62,77],"dynamic":[43],"range":[44],"(DRC).":[46],"also":[48],"propose":[49],"multi-regime":[50],"(MR)":[51],"design":[52],"the":[54,74],"nonlinearities,":[55],"at":[56],"improving":[57],"robustness.":[58],"Results":[59],"VoxCeleb1":[61],"VoxMovies":[63],"data":[64],"demonstrate":[65],"improvements":[66],"brought":[67],"by":[68],"proposed":[69],"over":[72],"both":[73],"commonly-used":[75],"logarithm":[76],"their":[78],"static":[79],"counterparts,":[80],"especially":[81],"ones":[83],"function.":[87],"While":[88],"CD":[89],"generalization":[90],"improves":[91],"performance":[92],"VoxCeleb1,":[94],"MR":[95],"provides":[96],"more":[97],"robustness":[98],"VoxMovies,":[100],"with":[101],"maximum":[103],"relative":[104],"equal":[105],"error":[106],"rate":[107],"reduction":[108],"21.6%.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
