{"id":"https://openalex.org/W3205310163","doi":"https://doi.org/10.1109/icassp43922.2022.9746178","title":"Multi-Query Multi-Head Attention Pooling and Inter-Topk Penalty for Speaker Verification","display_name":"Multi-Query Multi-Head Attention Pooling and Inter-Topk Penalty for Speaker Verification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205310163","doi":"https://doi.org/10.1109/icassp43922.2022.9746178","mag":"3205310163"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746178","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":"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/A5074355807","display_name":"Miao Zhao","orcid":"https://orcid.org/0000-0002-4324-1467"},"institutions":[{"id":"https://openalex.org/I4210114332","display_name":"Spencer Technologies (United States)","ror":"https://ror.org/02h1dyg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114332"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Zhao","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210114332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024989442","display_name":"Yufeng Ma","orcid":"https://orcid.org/0000-0003-2095-5739"},"institutions":[{"id":"https://openalex.org/I4210114332","display_name":"Spencer Technologies (United States)","ror":"https://ror.org/02h1dyg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114332"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufeng Ma","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210114332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000095400","display_name":"Yiwei Ding","orcid":"https://orcid.org/0000-0002-8156-3715"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210114332","display_name":"Spencer Technologies (United States)","ror":"https://ror.org/02h1dyg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114332"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yiwei Ding","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd","Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210114332"]},{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681023","display_name":"Yu Zheng","orcid":"https://orcid.org/0000-0002-5224-4344"},"institutions":[{"id":"https://openalex.org/I4210114332","display_name":"Spencer Technologies (United States)","ror":"https://ror.org/02h1dyg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114332"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zheng","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210114332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343919","display_name":"Min Liu","orcid":"https://orcid.org/0000-0002-8902-5460"},"institutions":[{"id":"https://openalex.org/I4210114332","display_name":"Spencer Technologies (United States)","ror":"https://ror.org/02h1dyg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114332"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Liu","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210114332"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100413867","display_name":"Minqiang Xu","orcid":"https://orcid.org/0000-0003-3625-1736"},"institutions":[{"id":"https://openalex.org/I4210114332","display_name":"Spencer Technologies (United States)","ror":"https://ror.org/02h1dyg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114332"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minqiang Xu","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210114332"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6737","last_page":"6741"},"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":0.9987999796867371,"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":0.9973999857902527,"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/pooling","display_name":"Pooling","score":0.8938735723495483},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8322935104370117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8149781227111816},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8149313926696777},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.595649003982544},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5913859009742737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47932112216949463},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4363028109073639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40507131814956665},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36007624864578247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35649919509887695},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.14989498257637024}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8938735723495483},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8322935104370117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149781227111816},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8149313926696777},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.595649003982544},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5913859009742737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47932112216949463},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4363028109073639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40507131814956665},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36007624864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35649919509887695},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.14989498257637024},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746178","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2803676284","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2932691488","https://openalex.org/W2949526695","https://openalex.org/W2962898354","https://openalex.org/W2963077989","https://openalex.org/W2963224870","https://openalex.org/W2969985801","https://openalex.org/W2970971581","https://openalex.org/W2972369255","https://openalex.org/W2972986505","https://openalex.org/W2973190269","https://openalex.org/W2981461916","https://openalex.org/W3024869864","https://openalex.org/W3093582452","https://openalex.org/W3094325190","https://openalex.org/W3095079700","https://openalex.org/W3095992690","https://openalex.org/W3103152812","https://openalex.org/W3109225549","https://openalex.org/W3135006803","https://openalex.org/W3141035251","https://openalex.org/W3146570934","https://openalex.org/W3174649707","https://openalex.org/W3197392277","https://openalex.org/W3198698812","https://openalex.org/W4286981691","https://openalex.org/W4288091954","https://openalex.org/W4295312788","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6748257384","https://openalex.org/W6751593755","https://openalex.org/W6766978945","https://openalex.org/W6769178842","https://openalex.org/W6784256521","https://openalex.org/W6784400926","https://openalex.org/W6784424227","https://openalex.org/W6801723603"],"related_works":["https://openalex.org/W3095152779","https://openalex.org/W3119773509","https://openalex.org/W3128220219","https://openalex.org/W2982889384","https://openalex.org/W4226227567","https://openalex.org/W3134502938","https://openalex.org/W2971218105","https://openalex.org/W3006353185","https://openalex.org/W4366375373","https://openalex.org/W3010284783"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,37,50,82,102,114],"multi-query":[4],"multi-head":[5,30],"attention":[6,31],"(MQMHA)":[7],"pooling":[8,32],"and":[9,61,104],"inter-topK":[10,93,105],"penalty":[11,94],"methods":[12],"which":[13],"were":[14],"first":[15],"proposed":[16,54],"in":[17,111],"our":[18],"submitted":[19],"system":[20],"description":[21],"for":[22],"VoxCeleb":[23,116],"speaker":[24,77],"recognition":[25],"challenge":[26],"(VoxSRC)":[27],"2021.":[28],"Most":[29],"mechanisms":[33,60],"either":[34],"attend":[35,44],"to":[36,45,74],"whole":[38,51],"feature":[39],"through":[40],"multiple":[41],"heads":[42],"or":[43],"several":[46],"split":[47],"parts":[48],"of":[49,113],"feature.":[52],"Our":[53],"MQMHA":[55,103],"combines":[56],"both":[57,101],"these":[58],"two":[59],"gain":[62],"more":[63],"diversified":[64],"information.":[65],"The":[66],"margin-based":[67],"softmax":[68],"loss":[69],"functions":[70],"are":[71],"commonly":[72],"adopted":[73],"obtain":[75],"discriminative":[76],"representations.":[78],"To":[79],"further":[80],"enhance":[81],"inter-class":[83],"discriminability,":[84],"we":[85,107],"propose":[86],"a":[87],"method":[88],"that":[89],"adds":[90],"an":[91],"extra":[92],"on":[95],"some":[96],"confused":[97],"speakers.":[98],"By":[99],"adopting":[100],"penalty,":[106],"achieved":[108],"state-of-the-art":[109],"performance":[110],"all":[112],"public":[115],"test":[117],"sets.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}