{"id":"https://openalex.org/W4323519273","doi":"https://doi.org/10.1109/tmm.2023.3253301","title":"Few-Shot Speaker Identification Using Lightweight Prototypical Network With Feature Grouping and Interaction","display_name":"Few-Shot Speaker Identification Using Lightweight Prototypical Network With Feature Grouping and Interaction","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323519273","doi":"https://doi.org/10.1109/tmm.2023.3253301"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3253301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3253301","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.19541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4362-1125","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353663","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0003-4339-3441"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055239917","display_name":"Wenchang Cao","orcid":"https://orcid.org/0009-0008-2790-2983"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchang Cao","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074527802","display_name":"Qisheng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qisheng Huang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070863631"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":2.3857,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90617139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"9241","last_page":"9253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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":0.9972000122070312,"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":0.9570000171661377,"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":0.8367051482200623},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6374302506446838},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5726147294044495},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5681425333023071},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5527698397636414},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5500487089157104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5469600558280945},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.48584792017936707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48446226119995117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4787706434726715},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4364379048347473},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4241736829280853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2060120701789856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367051482200623},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6374302506446838},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5726147294044495},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5681425333023071},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5527698397636414},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5500487089157104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5469600558280945},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.48584792017936707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48446226119995117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4787706434726715},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4364379048347473},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4241736829280853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2060120701789856},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2023.3253301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3253301","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2305.19541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19541","pdf_url":"https://arxiv.org/pdf/2305.19541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.19541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19541","pdf_url":"https://arxiv.org/pdf/2305.19541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3080163795","display_name":null,"funder_award_id":"2022A1515011687","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G3994375257","display_name":null,"funder_award_id":"61771200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6173053914","display_name":null,"funder_award_id":"62111530145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7284265120","display_name":null,"funder_award_id":"2021A1515011454","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4323519273.pdf","grobid_xml":"https://content.openalex.org/works/W4323519273.grobid-xml"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1509691205","https://openalex.org/W1821462560","https://openalex.org/W2034996255","https://openalex.org/W2046056978","https://openalex.org/W2050373581","https://openalex.org/W2121415728","https://openalex.org/W2128116588","https://openalex.org/W2131774270","https://openalex.org/W2140600286","https://openalex.org/W2141373863","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2171590421","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2303197844","https://openalex.org/W2553303224","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2612434969","https://openalex.org/W2747238065","https://openalex.org/W2808631503","https://openalex.org/W2887280559","https://openalex.org/W2888728808","https://openalex.org/W2890964092","https://openalex.org/W2897371647","https://openalex.org/W2914876604","https://openalex.org/W2928165649","https://openalex.org/W2938358845","https://openalex.org/W2939763029","https://openalex.org/W2962788625","https://openalex.org/W2963125010","https://openalex.org/W2963341924","https://openalex.org/W2963386851","https://openalex.org/W2963703618","https://openalex.org/W2964052309","https://openalex.org/W2974062151","https://openalex.org/W2980689481","https://openalex.org/W2981087920","https://openalex.org/W2982474723","https://openalex.org/W2998588665","https://openalex.org/W3009935550","https://openalex.org/W3012971850","https://openalex.org/W3014319644","https://openalex.org/W3015299720","https://openalex.org/W3015594652","https://openalex.org/W3049433044","https://openalex.org/W3088889289","https://openalex.org/W3093573519","https://openalex.org/W3095781422","https://openalex.org/W3096235116","https://openalex.org/W3104761488","https://openalex.org/W3114586009","https://openalex.org/W3128793294","https://openalex.org/W3137249133","https://openalex.org/W3145755065","https://openalex.org/W3164899004","https://openalex.org/W3190394743","https://openalex.org/W3205519288","https://openalex.org/W3215290109","https://openalex.org/W3216283037","https://openalex.org/W4200234408","https://openalex.org/W4205185612","https://openalex.org/W4205234379","https://openalex.org/W4224936492","https://openalex.org/W4226439436","https://openalex.org/W4234224867","https://openalex.org/W4246857368","https://openalex.org/W4285005022","https://openalex.org/W4285761028","https://openalex.org/W4292023222","https://openalex.org/W4297775537","https://openalex.org/W4297800219","https://openalex.org/W4298289240","https://openalex.org/W4366344170","https://openalex.org/W6637568146","https://openalex.org/W6638523607","https://openalex.org/W6684191040","https://openalex.org/W6717697761","https://openalex.org/W6729956949","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6737575990","https://openalex.org/W6737664043","https://openalex.org/W6743446608","https://openalex.org/W6761233929","https://openalex.org/W6775301260","https://openalex.org/W6781734511","https://openalex.org/W6782017022","https://openalex.org/W6784200033"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W2953234277","https://openalex.org/W4387678054","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183"],"abstract_inverted_index":{"Existing":[0],"methods":[1,179,213],"for":[2,21,72,83,141],"few-shot":[3],"speaker":[4,91,139],"identification":[5],"(FSSI)":[6],"obtain":[7],"high":[8],"accuracy,":[9],"but":[10],"their":[11],"computational":[12,78,215],"complexities":[13],"and":[14,55,77,80,130,158,168,193,207,217],"model":[15,218],"sizes":[16],"need":[17],"to":[18,41,68,136,177],"be":[19],"reduced":[20],"lightweight":[22,34],"applications.":[23],"In":[24,58,93],"this":[25],"work,":[26],"we":[27],"propose":[28],"a":[29,33,115,138,151,159],"FSSI":[30,44],"method":[31,174,200],"using":[32],"prototypical":[35,61],"network":[36],"with":[37,48],"the":[38,43,59,74,85,89,94,122],"final":[39],"goal":[40],"implement":[42],"on":[45,180],"intelligent":[46],"terminals":[47],"limited":[49],"resources,":[50],"such":[51],"as":[52],"smart":[53,56],"watches":[54],"speakers.":[57],"proposed":[60,95],"network,":[62],"an":[63],"embedding":[64,96,140],"module":[65],"is":[66,104,175],"designed":[67],"perform":[69],"feature":[70,81,99,109,166],"grouping":[71,167],"reducing":[73],"memory":[75],"requirement":[76],"complexity,":[79],"interaction":[82,169],"enhancing":[84],"representational":[86],"ability":[87],"of":[88,100,124,150,153,161],"learned":[90],"embedding.":[92],"module,":[97],"audio":[98],"each":[101,142],"speech":[102,143,189],"sample":[103],"split":[105],"into":[106],"several":[107,205],"low-dimensional":[108],"subsets":[110],"that":[111,183,198],"are":[112,133,170,184],"transformed":[113],"by":[114],"recurrent":[116,146],"convolutional":[117,147],"block":[118,148,152,160],"in":[119,164,214],"parallel.":[120],"Then,":[121],"operations":[123],"averaging,":[125],"addition,":[126],"concatenation,":[127],"element-wise":[128],"summation":[129],"statistics":[131],"pooling":[132],"sequentially":[134],"executed":[135],"learn":[137],"sample.":[144],"The":[145,195],"consists":[149],"bidirectional":[154],"long":[155],"short-term":[156],"memory,":[157],"de-redundancy":[162],"convolution":[163],"which":[165],"conducted":[171],"too.":[172],"Our":[173],"compared":[176],"baseline":[178,212],"three":[181,187],"datasets":[182],"selected":[185],"from":[186],"public":[188],"corpora":[190],"(VoxCeleb1,":[191],"VoxCeleb2,":[192],"LibriSpeech).":[194],"results":[196],"show":[197],"our":[199],"obtains":[201],"higher":[202],"accuracy":[203],"under":[204],"conditions,":[206],"has":[208],"advantages":[209],"over":[210],"all":[211],"complexity":[216],"size.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}