{"id":"https://openalex.org/W4402111679","doi":"https://doi.org/10.21437/interspeech.2024-2478","title":"A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition","display_name":"A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111679","doi":"https://doi.org/10.21437/interspeech.2024-2478"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2478","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2478","pdf_url":"https://www.isca-archive.org/interspeech_2024/zhou24f_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/zhou24f_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039042766","display_name":"Zhenyu Zhou","orcid":"https://orcid.org/0000-0002-3344-4463"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhou","raw_affiliation_strings":["Center for Speech and Language Technologies , BNRist , Tsinghua University , China","School of Artificial Intelligence , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies , BNRist , Tsinghua University , China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Artificial Intelligence , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011919230","display_name":"Shibiao Xu","orcid":"https://orcid.org/0000-0003-4037-9900"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibiao Xu","raw_affiliation_strings":["School of Artificial Intelligence , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101378678","display_name":"Shi Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Shi Yin","raw_affiliation_strings":["Huawei Technologies Co., Ltd. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd. , China","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["School of Artificial Intelligence , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391517","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-9599-8023"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies , BNRist , Tsinghua University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies , BNRist , Tsinghua University , China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5581,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83929667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2160","last_page":"2164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9889000058174133,"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":0.9889000058174133,"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":0.9807000160217285,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9028000235557556,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speaker-recognition","display_name":"Speaker recognition","score":0.8372716307640076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7042324542999268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6877803206443787},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5993791222572327},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4581091105937958}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.8372716307640076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042324542999268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6877803206443787},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5993791222572327},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4581091105937958}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-2478","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2478","pdf_url":"https://www.isca-archive.org/interspeech_2024/zhou24f_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-2478","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2478","pdf_url":"https://www.isca-archive.org/interspeech_2024/zhou24f_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111679.pdf","grobid_xml":"https://content.openalex.org/works/W4402111679.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W2545131480","https://openalex.org/W2249138175","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W4401661962","https://openalex.org/W2096510939","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,64],"(DA)":[2],"has":[3,39],"played":[4],"a":[5,81],"pivotal":[6],"role":[7],"in":[8,115,122],"the":[9,26,30,43,54,75,132,140,147],"success":[10],"of":[11,29,45,78,135,143,149],"deep":[12],"speaker":[13,27,46,63,116,144],"recognition.Current":[14],"DA":[15],"techniques":[16],"primarily":[17],"focus":[18],"on":[19,42],"speaker-preserving":[20],"augmentation,":[21,47,145],"which":[22,48],"does":[23,33],"not":[24,34],"change":[25],"trait":[28],"speech":[31],"and":[32,69,96,102,127,152],"create":[35],"new":[36,50,108],"speakers.Recent":[37],"research":[38,138],"shed":[40],"light":[41],"potential":[44,133,142],"generates":[49],"speakers":[51],"to":[52,111,124],"enrich":[53],"training":[55],"dataset.In":[56],"this":[57],"study,":[58,89],"we":[59],"delve":[60],"into":[61,84],"two":[62,92],"approaches:":[65],"speed":[66],"perturbation":[67,73,125],"(SP)":[68],"vocal":[70],"tract":[71],"length":[72],"(VTLP).Despite":[74],"empirical":[76],"utilization":[77],"both":[79,100],"methods,":[80],"comprehensive":[82],"investigation":[83],"their":[85,136],"efficacy":[86],"is":[87],"lacking.Our":[88],"conducted":[90],"using":[91],"public":[93],"datasets,":[94],"VoxCeleb":[95],"CN-Celeb,":[97],"revealed":[98],"that":[99],"SP":[101],"VTLP":[103],"are":[104],"proficient":[105],"at":[106,131],"generating":[107],"speakers,":[109],"leading":[110],"significant":[112],"performance":[113],"improvements":[114],"recognition.Furthermore,":[117],"they":[118],"exhibit":[119],"distinct":[120],"properties":[121],"sensitivity":[123],"factors":[126],"data":[128],"complexity,":[129],"hinting":[130],"benefits":[134],"fusion.Our":[137],"underscores":[139],"substantial":[141],"highlighting":[146],"importance":[148],"in-depth":[150],"exploration":[151],"analysis.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}