{"id":"https://openalex.org/W4221154745","doi":"https://doi.org/10.21437/interspeech.2022-563","title":"MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification","display_name":"MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221154745","doi":"https://doi.org/10.21437/interspeech.2022-563"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-563","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5100354683","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-4170-4798"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University","TEG AI, Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"TEG AI, Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033243530","display_name":"Zhiqiang Lv","orcid":"https://orcid.org/0000-0002-3071-160X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Lv","raw_affiliation_strings":["TEG AI, Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEG AI, Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University","Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412142","display_name":"Shanshan Zhang","orcid":"https://orcid.org/0000-0003-4013-6300"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Zhang","raw_affiliation_strings":["TEG AI, Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEG AI, Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703624","display_name":"Pengfei Hu","orcid":"https://orcid.org/0009-0000-4537-6288"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Hu","raw_affiliation_strings":["TEG AI, Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEG AI, Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University","Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":126,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"306","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9941999912261963,"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":0.9817000031471252,"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/conformational-isomerism","display_name":"Conformational isomerism","score":0.9092642664909363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6629108786582947},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6031755805015564},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5976001024246216},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5514772534370422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35386157035827637},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2110477089881897},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.1729375123977661},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08490943908691406},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.052183955907821655},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.050226569175720215}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.9092642664909363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6629108786582947},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6031755805015564},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5976001024246216},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5514772534370422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35386157035827637},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2110477089881897},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.1729375123977661},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08490943908691406},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.052183955907821655},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.050226569175720215},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-563","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329174","display_name":"Shenzhen Municipal Science and Technology Innovation Council","ror":"https://ror.org/017n8df75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2107638917","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916301830","https://openalex.org/W2928165649","https://openalex.org/W2962898354","https://openalex.org/W2964110616","https://openalex.org/W2970597249","https://openalex.org/W2972441390","https://openalex.org/W2972909277","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W3141035251","https://openalex.org/W3142516134","https://openalex.org/W3163842642","https://openalex.org/W3177318507","https://openalex.org/W3197478142","https://openalex.org/W3209984917","https://openalex.org/W4221154746","https://openalex.org/W4285666836","https://openalex.org/W4287374065","https://openalex.org/W4288091954","https://openalex.org/W4295312788","https://openalex.org/W4300943593","https://openalex.org/W4309845474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W3012606738","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W2052399476","https://openalex.org/W2077273959","https://openalex.org/W4385077663","https://openalex.org/W2810163160","https://openalex.org/W4220905048","https://openalex.org/W1578376090"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,42,56],"present":[4],"Multi-scale":[5],"Feature":[6],"Aggregation":[7],"Conformer":[8,58,81],"(MFA-Conformer),":[9],"an":[10],"easy-to-implement,":[11],"simple":[12],"but":[13,128],"effective":[14],"backbone":[15],"for":[16,161],"automatic":[17],"speaker":[18,40,152],"verification":[19],"based":[20],"on":[21,95,108],"the":[22,28,50,54,75,93,96,117,130,132,138,158],"Convolution-augmented":[23],"Transformer":[24],"(Conformer).The":[25],"architecture":[26],"of":[27,53,140],"MFA-Conformer":[29,94],"is":[30],"inspired":[31],"by":[32],"recent":[33],"stateof-the-art":[34],"models":[35],"in":[36,121],"speech":[37],"recognition":[38,123],"and":[39,63,71,105,111,125,142,150],"verification.Firstly,":[41],"introduce":[43],"a":[44],"convolution":[45,64],"subsampling":[46],"layer":[47],"to":[48,68,85,148],"decrease":[49],"computational":[51],"cost":[52],"model.Secondly,":[55],"adopt":[57],"blocks":[59,82],"which":[60],"combine":[61],"Transformers":[62],"neural":[65],"networks":[66],"(CNNs)":[67],"capture":[69],"global":[70,141],"local":[72,143],"features":[73],"effectively.Finally,":[74],"output":[76],"feature":[77,144],"maps":[78],"from":[79],"all":[80],"are":[83],"concatenated":[84],"aggregate":[86],"multi-scale":[87],"representations":[88],"before":[89],"final":[90],"pooling.We":[91],"evaluate":[92],"widely":[97],"used":[98],"benchmarks.The":[99],"best":[100],"system":[101],"obtains":[102],"0.64%,":[103],"1.29%":[104],"1.63%":[106],"EER":[107],"VoxCeleb1-O,":[109],"SITW.Dev,":[110],"SITW.Eval":[112],"set,":[113],"respectively.MFA-Conformer":[114],"significantly":[115],"outperforms":[116],"popular":[118],"ECAPA-TDNN":[119],"systems":[120],"both":[122],"performance":[124],"inference":[126],"speed.Last":[127],"not":[129],"least,":[131],"ablation":[133],"studies":[134],"clearly":[135],"demonstrate":[136],"that":[137],"combination":[139],"learning":[145],"can":[146],"lead":[147],"robust":[149],"accurate":[151],"embedding":[153],"extraction.We":[154],"have":[155],"also":[156],"released":[157],"code":[159],"1":[160],"future":[162],"comparison.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":48},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":10}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}