{"id":"https://openalex.org/W3096529494","doi":"https://doi.org/10.21437/interspeech.2020-1845","title":"Speaker Representation Learning Using Global Context Guided Channel and Time-Frequency Transformations","display_name":"Speaker Representation Learning Using Global Context Guided Channel and Time-Frequency Transformations","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096529494","doi":"https://doi.org/10.21437/interspeech.2020-1845","mag":"3096529494"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1845","doi":"https://doi.org/10.21437/interspeech.2020-1845","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1845","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2020","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.00768","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256","observed_orcids":["https://orcid.org/0009-0009-4734-6256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8585,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78120686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3226","last_page":"3230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9911999702453613,"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":0.9911999702453613,"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":0.005499999970197678,"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/T10828","display_name":"Biometric Identification and Security","score":0.00039999998989515007,"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/speaker-representation-learning","display_name":"speaker representation learning","score":0.8799999952316284},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"speaker verification","score":0.8740000128746033},{"id":"https://openalex.org/keywords/global-context","display_name":"global context","score":0.7400000095367432},{"id":"https://openalex.org/keywords/channel-attention","display_name":"channel attention","score":0.656000018119812},{"id":"https://openalex.org/keywords/time-frequency-transforms","display_name":"time-frequency transforms","score":0.8349999785423279},{"id":"https://openalex.org/keywords/non-local-dependencies","display_name":"non-local dependencies","score":0.7059999704360962},{"id":"https://openalex.org/keywords/feature-recalibration","display_name":"feature recalibration","score":0.8899999856948853},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.6240000128746033},{"id":"https://openalex.org/keywords/voxceleb1","display_name":"VoxCeleb1","score":0.9110000133514404},{"id":"https://openalex.org/keywords/lightweight-modules","display_name":"lightweight modules","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802646160125732},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7232497334480286},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.661672055721283},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6267793774604797},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5847674608230591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.54671710729599},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.514444887638092},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5112023949623108},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4526812434196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44357311725616455},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4248635470867157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41992253065109253},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41394996643066406},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41008105874061584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2164241373538971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13247236609458923},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13010674715042114},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-1845","doi":"https://doi.org/10.21437/interspeech.2020-1845","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1845","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.00768","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.00768","pdf_url":"https://arxiv.org/pdf/2009.00768","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2009.00768","doi":"https://doi.org/10.48550/arxiv.2009.00768","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.00768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.00768","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.00768","pdf_url":"https://arxiv.org/pdf/2009.00768","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096529494.pdf","grobid_xml":"https://content.openalex.org/works/W3096529494.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4380785258","https://openalex.org/W4394726722","https://openalex.org/W4296068991","https://openalex.org/W4226184234","https://openalex.org/W4317436846","https://openalex.org/W4316035551","https://openalex.org/W7162877044","https://openalex.org/W4206285316","https://openalex.org/W7196934916","https://openalex.org/W3015302980"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"propose":[4],"the":[5,15,28,43,46,65,78,99,105,110,130,133,141,146,167,184],"global":[6,29,47,176],"context":[7,30,48,177],"guided":[8,178],"channel":[9,21],"and":[10,20,36,49,96,109,159,191],"time-frequency":[11,18,39,190],"transformations":[12],"to":[13,32,104,123,153],"model":[14,90,108],"long-range,":[16],"non-local":[17],"dependencies":[19],"variances":[22],"in":[23,77,164],"speaker":[24,73,100,186],"representations.":[25],"We":[26,136],"use":[27],"information":[31],"enhance":[33],"important":[34],"channels":[35],"recalibrate":[37],"salient":[38],"locations":[40],"by":[41,113,139,188],"computing":[42],"similarity":[44],"between":[45],"local":[50],"features.":[51],"The":[52,170],"proposed":[53,134,142,175],"modules,":[54],"together":[55],"with":[56,91],"a":[57,70,88,114,155,160],"popular":[58],"ResNet":[59],"based":[60],"model,":[61],"are":[62,120],"evaluated":[63],"on":[64],"VoxCeleb1":[66],"dataset,":[67],"which":[68],"is":[69],"large":[71,115],"scale":[72],"verification":[74,101],"corpus":[75],"collected":[76],"wild.":[79],"This":[80],"lightweight":[81],"block":[82,112],"can":[83,181],"be":[84],"easily":[85],"incorporated":[86],"into":[87],"CNN":[89],"little":[92],"additional":[93],"computational":[94],"costs":[95],"effectively":[97],"improves":[98],"performance":[102,131],"compared":[103],"baseline":[106],"ResNet-LDE":[107],"Squeeze&Excitation":[111],"margin.":[116],"Detailed":[117],"ablation":[118],"studies":[119],"also":[121],"performed":[122],"analyze":[124],"various":[125],"factors":[126],"that":[127,138,173],"may":[128],"impact":[129],"of":[132,166],"modules.":[135],"find":[137],"employing":[140],"L2-tf-GTFC":[143],"transformation":[144,179],"block,":[145],"Equal":[147],"Error":[148],"Rate":[149],"decreases":[150],"from":[151],"4.56%":[152],"3.07%,":[154],"relative":[156,161],"32.68%":[157],"reduction,":[158],"27.28%":[162],"improvement":[163],"terms":[165],"DCF":[168],"score.":[169],"results":[171],"indicate":[172],"our":[174],"modules":[180],"efficiently":[182],"improve":[183],"learned":[185],"representations":[187],"achieving":[189],"channel-wise":[192],"feature":[193],"recalibration.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-11-09T00:00:00"}