{"id":"https://openalex.org/W3141483411","doi":"https://doi.org/10.1109/slt48900.2021.9383627","title":"Improving Speaker Recognition with Quality Indicators","display_name":"Improving Speaker Recognition with Quality Indicators","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3141483411","doi":"https://doi.org/10.1109/slt48900.2021.9383627","mag":"3141483411"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5087931356","display_name":"Hrishikesh Rao","orcid":"https://orcid.org/0000-0003-0972-3806"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hrishikesh Rao","raw_affiliation_strings":["Pindrop, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Pindrop, Atlanta, GA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006626628","display_name":"Kedar Phatak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kedar Phatak","raw_affiliation_strings":["Pindrop, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Pindrop, Atlanta, GA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010032071","display_name":"Elie Khoury","orcid":"https://orcid.org/0000-0001-9568-3729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elie Khoury","raw_affiliation_strings":["Pindrop, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Pindrop, Atlanta, GA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087931356"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03852615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.994700014591217,"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/speech-recognition","display_name":"Speech recognition","score":0.8176131248474121},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8033720850944519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870968580245972},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6451905965805054},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6209758520126343},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6134660840034485},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5408182144165039},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5310566425323486},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48765408992767334},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4734002351760864},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42346084117889404},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4233150780200958},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42275339365005493},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37375396490097046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30923205614089966},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10481974482536316},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08063682913780212}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8176131248474121},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8033720850944519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870968580245972},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6451905965805054},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6209758520126343},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6134660840034485},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5408182144165039},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5310566425323486},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48765408992767334},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4734002351760864},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42346084117889404},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4233150780200958},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42275339365005493},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37375396490097046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30923205614089966},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10481974482536316},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08063682913780212},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":29,"referenced_works":["https://openalex.org/W620149980","https://openalex.org/W1491421484","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1535817944","https://openalex.org/W1983134812","https://openalex.org/W1985360119","https://openalex.org/W2016770751","https://openalex.org/W2064364374","https://openalex.org/W2121812409","https://openalex.org/W2129066450","https://openalex.org/W2150769028","https://openalex.org/W2157161740","https://openalex.org/W2219249508","https://openalex.org/W2406312423","https://openalex.org/W2527729766","https://openalex.org/W2696967604","https://openalex.org/W2884535146","https://openalex.org/W2890964092","https://openalex.org/W2917756095","https://openalex.org/W2972961496","https://openalex.org/W6629497945","https://openalex.org/W6631362777","https://openalex.org/W6632239059","https://openalex.org/W6688816777","https://openalex.org/W6713727690","https://openalex.org/W6727697161","https://openalex.org/W6753583920","https://openalex.org/W6760207327"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205","https://openalex.org/W2150532155"],"abstract_inverted_index":{"Nuisance":[0],"factors":[1],"such":[2],"as":[3,51],"short":[4],"duration,":[5],"noise":[6],"and":[7,43],"transmission":[8],"conditions":[9],"still":[10],"pose":[11],"accuracy":[12],"challenges":[13],"to":[14,53,63,85,118],"state-of-the-art":[15],"automatic":[16],"speaker":[17,90],"verification":[18],"(ASV)":[19],"systems.":[20],"To":[21],"address":[22],"this":[23],"problem,":[24],"we":[25],"propose":[26],"a":[27,57,64,79,97,107],"no":[28],"reference":[29],"system":[30,82],"that":[31],"consumes":[32],"quality":[33,47],"indicators":[34,48],"encapsulating":[35],"information":[36],"about":[37],"duration":[38],"of":[39,89,100,110],"speech,":[40],"acoustic":[41],"events":[42],"codec":[44],"artifacts.":[45],"These":[46],"are":[49,83],"used":[50],"estimates":[52],"measure":[54],"how":[55],"close":[56],"given":[58],"speech":[59,66],"utterance":[60],"would":[61],"be":[62],"high-quality":[65],"segment":[67],"uttered":[68],"by":[69],"the":[70,87,101,119],"same":[71],"speaker.":[72],"The":[73,92],"proposed":[74],"measures":[75],"when":[76],"fused":[77],"with":[78],"baseline":[80],"ASV":[81],"found":[84],"improve":[86],"performance":[88],"recognition.":[91],"experimental":[93],"study":[94],"carried":[95],"on":[96],"modified":[98],"version":[99],"NIST":[102],"SRE":[103],"2019":[104],"dataset":[105],"shows":[106],"relative":[108],"decrease":[109],"9.6%":[111],"in":[112],"equal":[113],"error":[114],"rate":[115],"(EER)":[116],"compared":[117],"baseline.":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}