{"id":"https://openalex.org/W4285077987","doi":"https://doi.org/10.48550/arxiv.2207.04540","title":"Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning","display_name":"Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning","publication_year":2022,"publication_date":"2022-07-10","ids":{"openalex":"https://openalex.org/W4285077987","doi":"https://doi.org/10.48550/arxiv.2207.04540"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2207.04540","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.04540","pdf_url":"https://arxiv.org/pdf/2207.04540","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.04540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005211900","display_name":"Mufan Sang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sang, Mufan","raw_affiliation_strings":["Center for Robust Speech Systems , University of Texas at Dallas , TX 75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems , University of Texas at Dallas , TX 75080","institution_ids":["https://openalex.org/I162577319"]}]},{"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":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hansen, John H. L.","raw_affiliation_strings":["Center for Robust Speech Systems , University of Texas at Dallas , TX 75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems , University of Texas at Dallas , TX 75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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":0.9951000213623047,"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":0.00279999990016222,"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":0.00019999999494757503,"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-verification","display_name":"speaker verification","score":0.878000020980835},{"id":"https://openalex.org/keywords/speaker-representation-learning","display_name":"speaker representation learning","score":0.9169999957084656},{"id":"https://openalex.org/keywords/channel-attention","display_name":"channel attention","score":0.8270000219345093},{"id":"https://openalex.org/keywords/squeeze-and-excitation","display_name":"squeeze-and-excitation","score":0.9409999847412109},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"discrete cosine transform","score":0.8980000019073486},{"id":"https://openalex.org/keywords/time-frequency-decomposition","display_name":"time-frequency decomposition","score":0.5740000009536743},{"id":"https://openalex.org/keywords/global-average-pooling","display_name":"global average pooling","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771399974822998},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7218378186225891},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.651114821434021},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5979664921760559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5477331876754761},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5302298665046692},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5030156970024109},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48478907346725464},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4603208899497986},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4429362714290619},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43813008069992065},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4301438629627228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42943382263183594},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42267125844955444},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1157345175743103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10394883155822754},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08845680952072144},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2207.04540","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.04540","pdf_url":"https://arxiv.org/pdf/2207.04540","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.2207.04540","doi":"https://doi.org/10.48550/arxiv.2207.04540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2207.04540","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:2207.04540","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.04540","pdf_url":"https://arxiv.org/pdf/2207.04540","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285077987.pdf","grobid_xml":"https://content.openalex.org/works/W4285077987.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4226184234","https://openalex.org/W4372260481","https://openalex.org/W4301184462","https://openalex.org/W4220884846","https://openalex.org/W2981005517","https://openalex.org/W4313042211","https://openalex.org/W3131287090","https://openalex.org/W3134744625","https://openalex.org/W4319862221","https://openalex.org/W3096529494"],"abstract_inverted_index":{"Recently,":[0],"attention":[1,103,109,115,119,163],"mechanisms":[2],"have":[3],"been":[4],"applied":[5],"successfully":[6],"in":[7,50,81,184],"neural":[8,19],"network-based":[9],"speaker":[10,48,87,125,170],"verification":[11],"systems.":[12],"Incorporating":[13],"the":[14,35,51,77,86,132,141,149],"Squeeze-and-Excitation":[15],"block":[16],"into":[17],"convolutional":[18],"networks":[20],"has":[21],"achieved":[22],"remarkable":[23],"performance.":[24],"However,":[25],"it":[26],"uses":[27],"global":[28],"average":[29,34],"pooling":[30],"(GAP)":[31],"to":[32,93],"simply":[33],"features":[36],"along":[37],"time":[38],"and":[39,97,101,111,144,161,172,175,181],"frequency":[40,79,82,129],"dimensions,":[41],"which":[42],"is":[43,61],"incapable":[44],"of":[45,65,134],"preserving":[46],"sufficient":[47],"information":[49,88,96,126],"feature":[52],"maps.":[53],"In":[54],"this":[55],"study,":[56],"we":[57,91],"show":[58],"that":[59,157],"GAP":[60],"a":[62,66,145],"special":[63],"case":[64],"discrete":[67],"cosine":[68],"transform":[69],"(DCT)":[70],"on":[71,131,140,148],"time-frequency":[72],"domain":[73],"mathematically":[74],"using":[75],"only":[76],"lowest":[78],"component":[80],"decomposition.":[83],"To":[84],"strengthen":[85],"extraction":[89],"ability,":[90],"propose":[92],"utilize":[94],"multi-frequency":[95],"design":[98],"two":[99],"novel":[100],"effective":[102],"modules,":[104],"called":[105],"Single-Frequency":[106],"Single-Channel":[107,113],"(SFSC)":[108],"module":[110],"Multi-Frequency":[112],"(MFSC)":[114],"module.":[116],"The":[117],"proposed":[118,159],"modules":[120,164],"can":[121,165],"effectively":[122],"capture":[123],"more":[124,168],"from":[127],"multiple":[128],"components":[130],"basis":[133],"DCT.":[135],"We":[136],"conduct":[137],"comprehensive":[138],"experiments":[139],"VoxCeleb":[142],"datasets":[143],"probe":[146],"evaluation":[147],"1st":[150],"48-UTD":[151],"forensic":[152],"corpus.":[153],"Experimental":[154],"results":[155],"demonstrate":[156],"our":[158],"SFSC":[160],"MFSC":[162],"efficiently":[166],"generate":[167],"discriminative":[169],"representations":[171],"outperform":[173],"ResNet34-SE":[174],"ECAPA-TDNN":[176],"systems":[177],"with":[178],"relative":[179],"20.9%":[180],"20.2%":[182],"reduction":[183],"EER,":[185],"without":[186],"adding":[187],"extra":[188],"network":[189],"parameters.":[190]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2022-07-13T00:00:00"}