{"id":"https://openalex.org/W4382795444","doi":"https://doi.org/10.1186/s13636-023-00293-8","title":"Multi-task deep cross-attention networks for far-field speaker verification and keyword spotting","display_name":"Multi-task deep cross-attention networks for far-field speaker verification and keyword spotting","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4382795444","doi":"https://doi.org/10.1186/s13636-023-00293-8"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00293-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00293-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00293-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00293-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008366157","display_name":"Xingwei Liang","orcid":"https://orcid.org/0000-0002-5940-3440"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210093050","display_name":"Konka (China)","ror":"https://ror.org/00qa3c235","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093050"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Liang","raw_affiliation_strings":["Konka Group Co., Ltd, Shenzhen, China","School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Konka Group Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210093050"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090668921","display_name":"Zehua Zhang","orcid":"https://orcid.org/0000-0003-3215-5317"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Zhang","raw_affiliation_strings":["School of Electronics and Information Engineering, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026719663","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0002-4009-5679"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruifeng Xu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4009-5679","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026719663"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.4759,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67951037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"2023","issue":"1","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":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.8310315608978271},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8194912672042847},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6002967953681946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5455611944198608},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5216946005821228},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5122520327568054},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5097264647483826},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4894636869430542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4804215431213379},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45351946353912354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310315608978271},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8194912672042847},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6002967953681946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5455611944198608},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5216946005821228},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5122520327568054},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5097264647483826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4894636869430542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4804215431213379},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45351946353912354},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-023-00293-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00293-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00293-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:97d4f3b31c554fa986862342de246c51","is_oa":true,"landing_page_url":"https://doaj.org/article/97d4f3b31c554fa986862342de246c51","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-16 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00293-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00293-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00293-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2753377255","display_name":null,"funder_award_id":"62006062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3185807818","display_name":null,"funder_award_id":"62006062, 62176076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6083284296","display_name":null,"funder_award_id":"JCYJ20210324115614039","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G6312846351","display_name":null,"funder_award_id":"62176076","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"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382795444.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1977843990","https://openalex.org/W1998808035","https://openalex.org/W2034940213","https://openalex.org/W2046056978","https://openalex.org/W2049244943","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2407023693","https://openalex.org/W2748659049","https://openalex.org/W2752782242","https://openalex.org/W2784163702","https://openalex.org/W2888968865","https://openalex.org/W2889017397","https://openalex.org/W2890964092","https://openalex.org/W2896267789","https://openalex.org/W2903810591","https://openalex.org/W2913340405","https://openalex.org/W2938873567","https://openalex.org/W2956925952","https://openalex.org/W2963414149","https://openalex.org/W2963466847","https://openalex.org/W2963902346","https://openalex.org/W2969985801","https://openalex.org/W2972402291","https://openalex.org/W2972552635","https://openalex.org/W2972743990","https://openalex.org/W2973226577","https://openalex.org/W3003903817","https://openalex.org/W3008353833","https://openalex.org/W3010893827","https://openalex.org/W3010983946","https://openalex.org/W3015611708","https://openalex.org/W3016062729","https://openalex.org/W3019293601","https://openalex.org/W3021717829","https://openalex.org/W3024869864","https://openalex.org/W3096976027","https://openalex.org/W3103152812","https://openalex.org/W3104090442","https://openalex.org/W3173365702","https://openalex.org/W3197478142","https://openalex.org/W4214503194","https://openalex.org/W4226046733","https://openalex.org/W4283727191","https://openalex.org/W4312790276","https://openalex.org/W4360853195","https://openalex.org/W6600109629","https://openalex.org/W6603860191","https://openalex.org/W6604344240","https://openalex.org/W6610654676"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4389912005","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W2388033618","https://openalex.org/W105599799","https://openalex.org/W1483316057"],"abstract_inverted_index":{"Abstract":[0],"Personalized":[1,24],"voice":[2,9,22,25],"triggering":[3,26],"is":[4],"a":[5,50,78,108,120],"key":[6],"technology":[7],"in":[8,88,150,164,186,198],"assistants":[10],"and":[11,31,43,64,81,97,117,136,173,184,192,210],"serves":[12],"as":[13,92],"the":[14,21,54,101,128,133,143,151,165,176,193],"first":[15],"step":[16],"for":[17],"users":[18],"to":[19,37,71,85,114,126,141,145],"activate":[20],"assistant.":[23],"involves":[27],"keyword":[28],"spotting":[29],"(KWS)":[30],"speaker":[32],"verification":[33],"(SV).":[34],"Conventional":[35],"approaches":[36],"this":[38],"task":[39],"include":[40],"developing":[41],"KWS":[42,63,79,116,195],"SV":[44,83,118,178],"systems":[45],"separately.":[46],"This":[47],"paper":[48],"proposes":[49],"single":[51],"system":[52],"called":[53],"multi-task":[55],"deep":[56,110],"cross-attention":[57,111],"network":[58,190],"(MTCANet)":[59],"that":[60],"simultaneously":[61],"performs":[62],"SV,":[65],"while":[66,154],"effectively":[67],"utilizing":[68],"information":[69,149],"relevant":[70],"both":[72],"tasks.":[73],"The":[74],"proposed":[75,159],"framework":[76],"integrates":[77],"sub-network":[80,84],"an":[82],"enhance":[86],"performance":[87,163],"challenging":[89],"conditions":[90],"such":[91],"noisy":[93],"environments,":[94],"short-duration":[95],"speech,":[96],"model":[98,144,160,179,196],"generalization.":[99],"At":[100],"core":[102],"of":[103,130,200],"MTCANet":[104],"are":[105],"three":[106],"modules:":[107],"novel":[109],"(DCA)":[112],"module":[113],"integrate":[115],"tasks,":[119],"multi-layer":[121],"stacked":[122],"shared":[123],"encoder":[124],"(SE)":[125],"reduce":[127],"impact":[129],"noise":[131],"on":[132,147],"recognition":[134],"rate,":[135],"soft":[137],"attention":[138],"(SA)":[139],"modules":[140],"allow":[142],"focus":[146],"pertinent":[148],"middle":[152],"layer":[153],"preventing":[155],"gradient":[156],"vanishing.":[157],"Our":[158],"demonstrates":[161],"outstanding":[162],"well-off":[166],"test":[167],"set,":[168],"improving":[169],"by":[170],"0.2%,":[171],"0.023,":[172],"2.28%":[174],"over":[175],"well-known":[177],"emphasized":[180],"channel":[181],"attention,":[182],"propagation,":[183],"aggregation":[185],"time":[187],"delay":[188],"neural":[189],"(ECAPA-TDNN)":[191],"advanced":[194],"Convmixer":[197],"terms":[199],"equal":[201],"error":[202],"rate":[203],"(EER),":[204],"minimum":[205],"detection":[206],"cost":[207],"function":[208],"(minDCF),":[209],"accuracy":[211],"(Acc),":[212],"respectively.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}