{"id":"https://openalex.org/W4376456958","doi":"https://doi.org/10.1109/taslp.2023.3275029","title":"Model-Agnostic Meta-Learning for Fast Text-Dependent Speaker Embedding Adaptation","display_name":"Model-Agnostic Meta-Learning for Fast Text-Dependent Speaker Embedding Adaptation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4376456958","doi":"https://doi.org/10.1109/taslp.2023.3275029"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3275029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3275029","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5090644975","display_name":"Weiwei Lin","orcid":"https://orcid.org/0000-0002-9241-0271"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weiwei Lin","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9241-0271","affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8854-3760","affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.269,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82575439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"1866","last_page":"1876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9882000088691711,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.9121322631835938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8291899561882019},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7123879194259644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129087209701538},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5831871032714844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5572696328163147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.490057110786438}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.9121322631835938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291899561882019},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7123879194259644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129087209701538},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5831871032714844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5572696328163147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.490057110786438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3275029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3275029","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G2168692635","display_name":"\u7528\u4e8e\u57df\u4e0d\u53d8\u8bf4\u8bdd\u4eba\u9a8c\u8bc1\u7684\u6df1\u5c42\u5bf9\u6297\u7f51\u7edc","funder_award_id":"61971371","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1494198834","https://openalex.org/W1514535095","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2010362084","https://openalex.org/W2040105822","https://openalex.org/W2069143585","https://openalex.org/W2096733369","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2159786793","https://openalex.org/W2186774823","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2590440273","https://openalex.org/W2604763608","https://openalex.org/W2606778926","https://openalex.org/W2606786299","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2963446712","https://openalex.org/W2992306696","https://openalex.org/W3005680577","https://openalex.org/W3006713268","https://openalex.org/W3010079431","https://openalex.org/W3015503328","https://openalex.org/W3015585292","https://openalex.org/W3094665028","https://openalex.org/W3094735979","https://openalex.org/W3095352420","https://openalex.org/W3096127734","https://openalex.org/W3102719996","https://openalex.org/W3103152812","https://openalex.org/W3137249133","https://openalex.org/W3160744627","https://openalex.org/W3197848469","https://openalex.org/W4214503194","https://openalex.org/W4288091954","https://openalex.org/W4295312788","https://openalex.org/W4315778293","https://openalex.org/W6630875275","https://openalex.org/W6736057607","https://openalex.org/W6755365793","https://openalex.org/W6766978945","https://openalex.org/W6769178842","https://openalex.org/W6771326545","https://openalex.org/W6774314701","https://openalex.org/W6774379811","https://openalex.org/W6785214881"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2081900870","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2037549926","https://openalex.org/W2390154576"],"abstract_inverted_index":{"By":[0],"constraining":[1],"the":[2,53,64,75,85,88,99,105,111,116,136,161,181],"lexical":[3,30],"content":[4,31],"of":[5,149],"input":[6],"speech,":[7],"text-dependent":[8],"speaker":[9,18],"verification":[10,19],"(TD-SV)":[11],"offers":[12],"more":[13],"reliable":[14],"performance":[15,100],"than":[16],"text-independent":[17],"(TI-SV)":[20],"when":[21],"dealing":[22],"with":[23,28],"short":[24],"utterances.":[25],"Because":[26],"speech":[27,150],"constrained":[29],"is":[32,57,63,72,101,107,143],"harder":[33],"to":[34,73,131,159],"collect,":[35],"often":[36],"TD":[37,80,133,157],"models":[38],"are":[39],"fine-tuned":[40],"from":[41],"a":[42,46,123,128,132,140,146,155,173],"TI":[43,129,141,162],"model":[44,76,86,106,130,134,142,163],"using":[45,77,145,172],"small":[47,174],"target":[48,54,89,112,137,175,188],"phrase":[49,55,176,189],"dataset.":[50,177],"However,":[51],"sometimes":[52],"dataset":[56,158],"too":[58],"tiny":[59],"for":[60,67,110,126,135],"fine-tuning,":[61],"which":[62],"main":[65],"obstacle":[66],"deploying":[68],"TD-SV.":[69],"One":[70],"solution":[71],"fine-tune":[74],"medium-size":[78],"multi-phrase":[79,156,186],"data":[81],"and":[82,187],"then":[83],"deploy":[84],"on":[87],"phrase.":[90,113,138],"Although":[91],"this":[92],"strategy":[93],"does":[94],"help":[95],"in":[96,119],"some":[97],"cases,":[98],"still":[102],"sub-optimal":[103],"because":[104],"not":[108],"optimized":[109],"Inspired":[114],"by":[115],"recent":[117],"progress":[118],"meta-learning,":[120],"we":[121,153,168],"propose":[122],"three-stage":[124,182],"pipeline":[125,183],"adapting":[127],"Firstly,":[139],"trained":[144],"large":[147],"amount":[148],"data.":[151],"Then,":[152],"use":[154],"tune":[160],"via":[164],"model-agnostic":[165],"meta-learning.":[166],"Finally,":[167],"perform":[169],"fast":[170],"adaptation":[171],"Results":[178],"show":[179],"that":[180],"consistently":[184],"outperforms":[185],"fine-tuning.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}