{"id":"https://openalex.org/W4402112243","doi":"https://doi.org/10.21437/interspeech.2024-161","title":"On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models","display_name":"On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112243","doi":"https://doi.org/10.21437/interspeech.2024-161"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-161","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-161","pdf_url":null,"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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027476226","display_name":"Mengjie Qian","orcid":"https://orcid.org/0000-0003-2614-5411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengjie Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Gales","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042184515"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.62,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86140134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3774","last_page":"3778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9915000200271606,"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":0.9915000200271606,"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":0.9398999810218811,"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/T10860","display_name":"Speech and Audio Processing","score":0.9174000024795532,"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/speaker-recognition","display_name":"Speaker recognition","score":0.6989791989326477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6961848735809326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6836391687393188},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6125394105911255},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5718242526054382},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5427115559577942},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5049496293067932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48160287737846375},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.46689069271087646}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6989791989326477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961848735809326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6836391687393188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6125394105911255},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5718242526054382},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5427115559577942},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5049496293067932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48160287737846375},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.46689069271087646}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-161","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:doi:10.17863/cam.109340","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"}],"best_oa_location":{"id":"pmh:doi:10.17863/cam.109340","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4598575966","display_name":null,"funder_award_id":"EP/V006223/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","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"],"abstract_inverted_index":{"In":[0,23],"this":[1,24],"paper,":[2],"we":[3,83,121],"investigate":[4],"the":[5,8,19,45,49,54,66,90,101,108,115,123],"efficacy":[6],"of":[7,110,117],"widely-used":[9],"xvector":[10],"and":[11,96,103,113,129,137],"ECAPA-TDNN":[12,97],"speaker":[13,16,41,86],"embeddings":[14,98,112],"for":[15,62],"retrieval":[17,42,87],"on":[18],"BBC":[20],"Rewind":[21],"corpus.":[22],"archival":[25],"collection":[26],"each":[27],"file":[28],"is":[29,37],"briefly":[30],"described":[31],"by":[32],"a":[33,40,85],"synopsis.":[34],"Our":[35],"objective":[36],"to":[38,75],"develop":[39,84],"system,":[43],"treating":[44],"names":[46],"mentioned":[47],"in":[48,135],"synopses":[50],"as":[51,131,133],"speakers.":[52],"However,":[53],"provided":[55],"labels":[56],"exhibit":[57],"significant":[58],"noise,":[59],"posing":[60],"challenges":[61],"model":[63],"training.":[64],"Further,":[65],"dataset":[67],"encompasses":[68],"diverse":[69],"acoustic":[70],"conditions,":[71],"ranging":[72],"from":[73,100],"clean":[74],"highly":[76],"noisy":[77],"environments.":[78],"To":[79],"address":[80],"these":[81,111],"challenges,":[82],"system":[88],"\u201cin":[89],"wild\u201d":[91],"via":[92],"leveraging":[93],"pre-trained":[94],"x-vector":[95],"models":[99],"SpeechBrain":[102],"NeMo":[104],"toolkits.":[105],"We":[106],"assess":[107],"effectiveness":[109],"explore":[114],"usefulness":[116],"their":[118],"combination.":[119],"Additionally,":[120],"evaluate":[122],"models'":[124],"robustness":[125],"against":[126],"additive":[127],"noise":[128],"reverberation":[130],"well":[132],"variations":[134],"bit-depth":[136],"sampling":[138],"rate.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}