{"id":"https://openalex.org/W4206285316","doi":"https://doi.org/10.1109/lsp.2021.3136141","title":"Dynamic Convolution With Global-Local Information for Session-Invariant Speaker Representation Learning","display_name":"Dynamic Convolution With Global-Local Information for Session-Invariant Speaker Representation Learning","publication_year":2021,"publication_date":"2021-12-16","ids":{"openalex":"https://openalex.org/W4206285316","doi":"https://doi.org/10.1109/lsp.2021.3136141"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3136141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3136141","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1621-7311","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.8189,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7872035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"404","last_page":"408"},"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":0.9987000226974487,"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":0.9977999925613403,"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":0.7928244471549988},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7211853265762329},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.595980167388916},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5868387222290039},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5862107872962952},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5769931077957153},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5308505296707153},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5037681460380554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46415671706199646},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4222484827041626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40161678194999695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38103288412094116},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35094866156578064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09137535095214844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928244471549988},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7211853265762329},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.595980167388916},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5868387222290039},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5862107872962952},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5769931077957153},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5308505296707153},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5037681460380554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46415671706199646},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4222484827041626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40161678194999695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38103288412094116},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35094866156578064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09137535095214844},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2021.3136141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3136141","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2079623482","https://openalex.org/W2398776621","https://openalex.org/W2404617565","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2889016587","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2916058012","https://openalex.org/W2935898178","https://openalex.org/W2937328535","https://openalex.org/W2938358845","https://openalex.org/W2963418523","https://openalex.org/W2964307722","https://openalex.org/W2972885011","https://openalex.org/W2973099347","https://openalex.org/W2978904488","https://openalex.org/W3006741730","https://openalex.org/W3015231328","https://openalex.org/W3015261361","https://openalex.org/W3015964387","https://openalex.org/W3020953549","https://openalex.org/W3096529494","https://openalex.org/W3096761643","https://openalex.org/W3097244734","https://openalex.org/W3097298049","https://openalex.org/W3197111314","https://openalex.org/W3198041020","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W3034421924","https://openalex.org/W4386858688","https://openalex.org/W2982536526","https://openalex.org/W204267554","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W2134501921"],"abstract_inverted_index":{"Various":[0],"mismatchedconditions":[1],"result":[2],"in":[3],"performance":[4],"degradation":[5],"of":[6,39,57,88],"the":[7,31,40,48,54,64,83,89],"speaker":[8,19,59],"verification":[9],"(SV)":[10],"systems.":[11],"To":[12],"address":[13],"this":[14],"issue,":[15],"we":[16],"extract":[17],"robust":[18],"representations":[20],"by":[21,61],"devising":[22],"a":[23],"global-local":[24],"information-based":[25],"dynamic":[26],"convolution":[27,49],"neural":[28],"network.":[29],"In":[30],"proposed":[32,90],"method,":[33],"both":[34,63],"global":[35],"and":[36,66,79,98],"local":[37],"information":[38],"input":[41],"features":[42],"are":[43],"exploited":[44],"to":[45],"dynamically":[46],"modify":[47],"kernel":[50],"values.":[51],"This":[52],"increases":[53],"model":[55],"capability":[56],"capturing":[58],"characteristics":[60],"compensating":[62],"inter-":[65],"intra-session":[67],"variabilities.":[68],"Extensive":[69],"experiments":[70],"on":[71],"four":[72],"publicly":[73],"available":[74],"SV":[75],"datasets":[76],"show":[77],"significant":[78],"consistent":[80],"improvements":[81],"over":[82],"conventional":[84],"approaches.":[85],"The":[86],"effectiveness":[87],"method":[91],"is":[92],"further":[93],"investigated":[94],"using":[95],"ablation":[96],"studies":[97],"visualizations.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}