{"id":"https://openalex.org/W4387411751","doi":"https://doi.org/10.1109/icrera59003.2023.10269366","title":"Data Augmentation with ECAPA-TDNN Architecture for Automatic Speaker Recognition","display_name":"Data Augmentation with ECAPA-TDNN Architecture for Automatic Speaker Recognition","publication_year":2023,"publication_date":"2023-08-29","ids":{"openalex":"https://openalex.org/W4387411751","doi":"https://doi.org/10.1109/icrera59003.2023.10269366"},"language":"en","primary_location":{"id":"doi:10.1109/icrera59003.2023.10269366","doi":"https://doi.org/10.1109/icrera59003.2023.10269366","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icrera59003.2023.10269366","pdf_url":null,"source":{"id":"https://openalex.org/S4306497889","display_name":"International Conference on Renewable Energy Research and Applications (ICRERA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 12th International Conference on Renewable Energy Research and Applications (ICRERA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5109644750","display_name":"Pinyan Li","orcid":"https://orcid.org/0009-0001-4716-1229","observed_orcids":["https://orcid.org/0009-0001-4716-1229"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Pinyan Li","raw_affiliation_strings":["Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078266731","display_name":"Lap Man Hoi","orcid":"https://orcid.org/0000-0002-1074-9846","observed_orcids":["https://orcid.org/0000-0002-1074-9846"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Lap Man Hoi","raw_affiliation_strings":["Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101760165","display_name":"Yapeng Wang","orcid":"https://orcid.org/0000-0002-1085-5091","observed_orcids":["https://orcid.org/0000-0002-1085-5091"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yapeng Wang","raw_affiliation_strings":["Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022394682","display_name":"Sio\u2010Kei Im","orcid":"https://orcid.org/0000-0002-5599-4300","observed_orcids":["https://orcid.org/0000-0002-5599-4300"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Sio Kei Im","raw_affiliation_strings":["Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":null,"apc_paid":null,"fwci":0.3314,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53253921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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":9.999999747378752e-05,"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/data-augmentation","display_name":"data augmentation","score":0.9100000262260437},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.8199999928474426},{"id":"https://openalex.org/keywords/ecapa-tdnn","display_name":"ECAPA-TDNN","score":0.996999979019165},{"id":"https://openalex.org/keywords/channel-attention","display_name":"channel attention","score":0.6949999928474426},{"id":"https://openalex.org/keywords/training-data-diversity","display_name":"training data diversity","score":0.6100000143051147},{"id":"https://openalex.org/keywords/speaker-classification","display_name":"speaker classification","score":0.4830000102519989},{"id":"https://openalex.org/keywords/number-of-layers","display_name":"number of layers","score":0.5149999856948853},{"id":"https://openalex.org/keywords/voxceleb","display_name":"VoxCeleb","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102928400039673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6718276739120483},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.580588698387146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5488772988319397},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5232504606246948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5184873342514038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5033754706382751},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.45235520601272583},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.41874033212661743},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1379224956035614},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icrera59003.2023.10269366","doi":"https://doi.org/10.1109/icrera59003.2023.10269366","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icrera59003.2023.10269366","pdf_url":null,"source":{"id":"https://openalex.org/S4306497889","display_name":"International Conference on Renewable Energy Research and Applications (ICRERA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 12th International Conference on Renewable Energy Research and Applications (ICRERA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2890964092","https://openalex.org/W2891138528","https://openalex.org/W2971926373","https://openalex.org/W2984189102","https://openalex.org/W3006741730","https://openalex.org/W3024869864","https://openalex.org/W3049278490","https://openalex.org/W3121150787","https://openalex.org/W3123761700","https://openalex.org/W3143367551","https://openalex.org/W3171302872","https://openalex.org/W3176848203","https://openalex.org/W3212357841","https://openalex.org/W4225325562","https://openalex.org/W4289713394","https://openalex.org/W4319586596","https://openalex.org/W4327782440","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W3006741730","https://openalex.org/W4372271607","https://openalex.org/W4327521002","https://openalex.org/W4385719553","https://openalex.org/W4407569553","https://openalex.org/W3157702387","https://openalex.org/W4416799023","https://openalex.org/W4393977829","https://openalex.org/W4403702685","https://openalex.org/W3147246185"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,9,62,112],"seven":[4,109],"data":[5,28,110],"augmentation":[6],"methods":[7],"based":[8],"the":[10,24,50,55,58,63,68,73,76,85,91,95,120,125,132,138,144,148],"Emphasized":[11],"Channel":[12],"Attention":[13],"Propagation":[14],"and":[15,33,48,87,90,99,124],"Aggregation-Time":[16],"Delay":[17],"Neural":[18],"Network":[19],"(ECAPA-TDNN)":[20],"model":[21,31,97],"for":[22],"increasing":[23],"diversity":[25],"of":[26,57,60,70,72,147],"training":[27],"to":[29,42,136],"improve":[30,43],"accuracy":[32,98,117],"true":[34],"positive":[35],"rate":[36],"(TPR/recall).":[37],"We":[38,52,129],"propose":[39],"a":[40,113],"method":[41,81],"classification":[44,64,100,145],"performance":[45,65,101,146],"by":[46,66,105],"replacing":[47],"reducing":[49],"datasets.":[51],"also":[53,130],"verified":[54],"effect":[56],"number":[59,69],"layers":[61,71],"modifying":[67],"SE-Res2Block":[74],"in":[75],"ECAPA-TDNN":[77],"model.":[78,149],"The":[79,116],"proposed":[80],"is":[82],"validated":[83],"with":[84,108],"ZhVoice":[86,107],"VoxCeleb":[88],"datasets,":[89],"results":[92],"show":[93],"that":[94],"best":[96],"can":[102],"be":[103],"obtained":[104],"using":[106],"augmentations":[111],"3-layer":[114],"SE-Res2Block.":[115],"reached":[118,122],"0.9477,":[119],"TPR":[121],"0.8945,":[123],"EER":[126],"was":[127],"0.1278.":[128],"used":[131],"diagonal":[133],"cosine":[134],"algorithm":[135],"determine":[137],"similarity":[139],"between":[140],"two":[141],"speakers,":[142],"validating":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-07T00:00:00"}