{"id":"https://openalex.org/W4416771661","doi":"https://doi.org/10.1109/sped67700.2025.11254709","title":"From Lab to Field: Practical Deployment and Evaluation of a Speaker Recognition System","display_name":"From Lab to Field: Practical Deployment and Evaluation of a Speaker Recognition System","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771661","doi":"https://doi.org/10.1109/sped67700.2025.11254709"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11254709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11254709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-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/A5120388175","display_name":"Raluca-Ionela Costan","orcid":null},"institutions":[{"id":"https://openalex.org/I2802885015","display_name":"Military Technical Academy","ror":"https://ror.org/01tqmsq19","country_code":"RO","type":"education","lineage":["https://openalex.org/I2802885015"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Raluca-Ionela Costan","raw_affiliation_strings":["Military Technical Academy “Ferdinand I”,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"Military Technical Academy “Ferdinand I”,Bucharest,Romania","institution_ids":["https://openalex.org/I2802885015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021376776","display_name":"Mihai Coca","orcid":"https://orcid.org/0000-0003-2434-7554"},"institutions":[{"id":"https://openalex.org/I2802885015","display_name":"Military Technical Academy","ror":"https://ror.org/01tqmsq19","country_code":"RO","type":"education","lineage":["https://openalex.org/I2802885015"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mihai Coca","raw_affiliation_strings":["Military Technical Academy “Ferdinand I”,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"Military Technical Academy “Ferdinand I”,Bucharest,Romania","institution_ids":["https://openalex.org/I2802885015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069948679","display_name":"\u0218tefan-Adrian Toma","orcid":"https://orcid.org/0000-0001-5073-4617"},"institutions":[{"id":"https://openalex.org/I2802885015","display_name":"Military Technical Academy","ror":"https://ror.org/01tqmsq19","country_code":"RO","type":"education","lineage":["https://openalex.org/I2802885015"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"\u015etefan-Adrian Toma","raw_affiliation_strings":["Military Technical Academy “Ferdinand I”,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"Military Technical Academy “Ferdinand I”,Bucharest,Romania","institution_ids":["https://openalex.org/I2802885015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120388175"],"corresponding_institution_ids":["https://openalex.org/I2802885015"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20611281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.777400016784668,"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":0.777400016784668,"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":0.1234000027179718,"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":0.03020000085234642,"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/software-deployment","display_name":"Software deployment","score":0.6500999927520752},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6039000153541565},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5593000054359436},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.531000018119812},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5023999810218811},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.38960000872612},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.3894999921321869},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.3880999982357025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343999743461609},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6366999745368958},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2897000014781952},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C81293917","wikidata":"https://www.wikidata.org/wiki/Q4189534","display_name":"System deployment","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11254709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11254709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2041823554","https://openalex.org/W2150769028","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W3024869864","https://openalex.org/W3038871978","https://openalex.org/W3159987579","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4281687945","https://openalex.org/W4319862221","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385822752","https://openalex.org/W4402594946"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,8,35,82,105,149],"field":[2],"of":[3,12,28,57,65,101,107,111,156],"speech":[4],"signal":[5],"processing,":[6],"both":[7],"duration":[9,120],"and":[10,19,38,53,74,98,117,142,152],"quality":[11],"audio":[13,119],"recordings":[14],"significantly":[15],"influence":[16],"system":[17,32,58,129],"performance":[18,130],"response":[20],"time.":[21,127],"This":[22],"work":[23],"presents":[24],"a":[25,29,41,63,85,99],"comprehensive":[26],"evaluation":[27,61],"speaker":[30,86,158],"recognition":[31,159],"developed":[33],"using":[34,81,137],"SpeechBrain":[36,73],"toolkit":[37],"deployed":[39],"within":[40],"containerized":[42],"application.Six":[43],"experimental":[44],"scenarios":[45],"were":[46],"designed":[47],"to":[48,115,122],"reflect":[49],"real-world":[50],"usage":[51],"conditions":[52],"explore":[54],"various":[55],"dimensions":[56],"performance.":[59],"The":[60],"includes":[62],"comparison":[64],"two":[66],"voice":[67],"activity":[68],"detection":[69],"(VAD)":[70],"models":[71],"\u2014":[72,76],"Silero":[75],"in":[77],"multi-speaker":[78],"noisy":[79],"environments":[80],"VoxConverse":[83],"dataset;":[84],"re-identification":[87],"test":[88,118],"measuring":[89],"Equal":[90],"Error":[91],"Rate":[92],"(EER)":[93],"across":[94],"multiple":[95],"segmentation":[96],"configurations;":[97],"set":[100],"scalability":[102],"tests":[103],"analyzing":[104],"impact":[106],"CPU":[108,140],"threading,":[109],"number":[110],"enrolled":[112],"users":[113],"(up":[114,121],"15,000),":[116],"24":[123],"hours)":[124],"on":[125],"processing":[126],"Additionally,":[128],"was":[131],"measured":[132],"under":[133],"full":[134],"hardware":[135],"utilization":[136],"all":[138],"available":[139],"cores":[141],"GPUs.":[143],"Results":[144],"offer":[145],"valuable":[146],"insights":[147],"into":[148],"efficiency,":[150],"robustness,":[151],"practical":[153],"deployment":[154],"considerations":[155],"open-source":[157],"solutions.":[160]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}