{"id":"https://openalex.org/W3015503328","doi":"https://doi.org/10.1109/icassp40776.2020.9054423","title":"HI-MIA: A Far-Field Text-Dependent Speaker Verification Database and the Baselines","display_name":"HI-MIA: A Far-Field Text-Dependent Speaker Verification Database and the Baselines","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015503328","doi":"https://doi.org/10.1109/icassp40776.2020.9054423","mag":"3015503328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5075605099","display_name":"Xiaoyi Qin","orcid":"https://orcid.org/0000-0003-2521-8084"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyi Qin","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0002-5883-1195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":["Beijing Shell Shell Technology Co. Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Shell Shell Technology Co. Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075605099"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":6.9706,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.97873601,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7609","last_page":"7613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.8056159615516663},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6944657564163208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6484724283218384},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6383237838745117},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5793341398239136},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5491459965705872},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5414701700210571},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.4926221966743469},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4810790717601776},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4652474820613861},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4424106478691101},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3552815020084381},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34407639503479004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3395634591579437},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10220059752464294},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09393832087516785},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07316941022872925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056159615516663},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6944657564163208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6484724283218384},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6383237838745117},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5793341398239136},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5491459965705872},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5414701700210571},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.4926221966743469},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4810790717601776},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4652474820613861},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4424106478691101},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3552815020084381},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34407639503479004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3395634591579437},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10220059752464294},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09393832087516785},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07316941022872925},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1983812858","https://openalex.org/W2016449517","https://openalex.org/W2055611715","https://openalex.org/W2062470372","https://openalex.org/W2108327698","https://openalex.org/W2114719288","https://openalex.org/W2118479009","https://openalex.org/W2150769028","https://openalex.org/W2153485077","https://openalex.org/W2158143227","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2326699523","https://openalex.org/W2398042854","https://openalex.org/W2402919203","https://openalex.org/W2513927927","https://openalex.org/W2586068394","https://openalex.org/W2726515241","https://openalex.org/W2763188033","https://openalex.org/W2793459270","https://openalex.org/W2799831802","https://openalex.org/W2808631503","https://openalex.org/W2888955371","https://openalex.org/W2889048668","https://openalex.org/W2890964092","https://openalex.org/W2963371159","https://openalex.org/W2972311940","https://openalex.org/W2972315886","https://openalex.org/W6629717138","https://openalex.org/W6688816777","https://openalex.org/W6733312898","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W1977167953","https://openalex.org/W2150532155","https://openalex.org/W2253551762","https://openalex.org/W2610950809","https://openalex.org/W4310621200","https://openalex.org/W1585307611","https://openalex.org/W2121417792","https://openalex.org/W2131469787","https://openalex.org/W1552703621","https://openalex.org/W1570576710"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,69,76,94],"far-field":[4,19,50,118,132],"text-dependent":[5],"speaker":[6,23,67],"verification":[7,24],"database":[8,39],"named":[9],"HI-MIA.":[10],"We":[11],"aim":[12],"to":[13,65,101],"meet":[14],"the":[15,28,49,66,104,109,117,128],"data":[16,88],"requirement":[17],"for":[18,48,89],"microphone":[20,57],"array":[21],"based":[22,82],"since":[25],"most":[26],"of":[27,42,78],"publicly":[29],"available":[30],"databases":[31],"are":[32,53],"single":[33],"channel":[34],"close-talking":[35,71,129],"and":[36,63,68,124,131],"text-independent.":[37],"The":[38],"contains":[40],"recordings":[41],"340":[43],"people":[44],"in":[45,60,116,127],"rooms":[46],"designed":[47],"scenario.":[51],"Recordings":[52],"captured":[54],"by":[55],"multiple":[56],"arrays":[58],"located":[59],"different":[61],"directions":[62],"distance":[64],"high-fidelity":[70],"microphone.":[72],"Besides,":[73],"we":[74,92],"propose":[75,93],"set":[77],"end-to-end":[79],"neural":[80],"network":[81],"baseline":[83],"systems":[84,111],"that":[85,108],"adopt":[86],"single-channel":[87],"training.":[90],"Moreover,":[91],"testing":[95,122,133],"background":[96],"aware":[97],"enrollment":[98,119,130],"augmentation":[99],"strategy":[100],"further":[102],"enhance":[103],"performance.":[105],"Results":[106],"show":[107],"fusion":[110],"could":[112],"achieve":[113],"3.29%":[114],"EER":[115,126],"far":[120],"field":[121],"task":[123],"4.02%":[125],"task.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}