{"id":"https://openalex.org/W4244852473","doi":"https://doi.org/10.23919/eusipco54536.2021.9616242","title":"Voice-quality Features for Deep Neural Network Based Speaker Verification Systems","display_name":"Voice-quality Features for Deep Neural Network Based Speaker Verification Systems","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4244852473","doi":"https://doi.org/10.23919/eusipco54536.2021.9616242"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616242","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616242","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5073024862","display_name":"Abraham Woubie","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Abraham Woubie","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067143321","display_name":"Lauri Koivisto","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Koivisto","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052130850","display_name":"Tom B\u00e4ckstr\u00f6m","orcid":"https://orcid.org/0000-0002-5590-2349"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tom Backstrom","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073024862"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.8796,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78612825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"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":0.9991000294685364,"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":0.9961000084877014,"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/spectrogram","display_name":"Spectrogram","score":0.9010944366455078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415881156921387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7285418510437012},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.6952107548713684},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6350365877151489},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.612199604511261},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5293384790420532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5268584489822388},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47274598479270935},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4697965383529663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4611220061779022},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.061289459466934204}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9010944366455078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415881156921387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7285418510437012},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.6952107548713684},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6350365877151489},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.612199604511261},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5293384790420532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5268584489822388},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47274598479270935},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4697965383529663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611220061779022},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.061289459466934204},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616242","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616242","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8471362617","display_name":null,"funder_award_id":"700795","funder_id":"https://openalex.org/F4320322282","funder_display_name":"Jane ja Aatos Erkon S\u00e4\u00e4ti\u00f6"}],"funders":[{"id":"https://openalex.org/F4320322282","display_name":"Jane ja Aatos Erkon S\u00e4\u00e4ti\u00f6","ror":"https://ror.org/03vxy9y38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W44948719","https://openalex.org/W191366985","https://openalex.org/W579783719","https://openalex.org/W1538905335","https://openalex.org/W1907851480","https://openalex.org/W1987759408","https://openalex.org/W2016125416","https://openalex.org/W2102518334","https://openalex.org/W2128915671","https://openalex.org/W2164512637","https://openalex.org/W2240726287","https://openalex.org/W2482731677","https://openalex.org/W2515837905","https://openalex.org/W2726515241","https://openalex.org/W2790216641","https://openalex.org/W2808631503","https://openalex.org/W2892997601","https://openalex.org/W2972392008","https://openalex.org/W6616832263","https://openalex.org/W6639851569","https://openalex.org/W6679243561","https://openalex.org/W6695659996","https://openalex.org/W6740167877","https://openalex.org/W6748832432","https://openalex.org/W6755366624"],"related_works":["https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Jitter":[0],"and":[1,15,93],"shimmer":[2],"are":[3,53],"voice-quality":[4,29],"features":[5,30,96],"which":[6,113],"have":[7],"been":[8],"successfully":[9],"used":[10,66],"to":[11,56,67,109],"detect":[12],"voice":[13,94],"pathologies":[14],"classify":[16],"different":[17],"speaking":[18],"styles.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"investigate":[24],"the":[25,44,50,82,85,91,110],"usefulness":[26],"of":[27,42,84],"such":[28],"in":[31,103],"neural-network":[32],"based":[33,115],"speaker":[34],"verification":[35],"systems.":[36],"To":[37],"combine":[38],"these":[39],"two":[40,51],"sets":[41,52],"features,":[43],"cosine":[45,86],"distance":[46,87],"scores":[47,88],"estimated":[48],"from":[49,90],"linearly":[54],"weighted":[55],"obtain":[57],"a":[58,69,98],"single,":[59],"fused":[60,63],"score.":[61],"The":[62,72],"score":[64],"is":[65,114],"accept/reject":[68],"given":[70],"speaker.":[71],"experimental":[73],"results":[74],"carried":[75],"out":[76],"on":[77,117],"Voxceleb-1":[78],"dataset":[79],"demonstrate":[80],"that":[81],"fusion":[83],"extracted":[89],"mel-spectrogram":[92,118],"quality":[95],"provide":[97],"15":[99],"%":[100],"relative":[101],"improvement":[102],"Equal":[104],"Error":[105],"Rate":[106],"(EER)":[107],"compared":[108],"baseline":[111],"system":[112],"only":[116],"features.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-05-12T00:00:00"}
