{"id":"https://openalex.org/W2983586762","doi":"https://doi.org/10.23919/eusipco.2019.8902646","title":"Non-Intrusive POLQA Estimation of Speech Quality using Recurrent Neural Networks","display_name":"Non-Intrusive POLQA Estimation of Speech Quality using Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2983586762","doi":"https://doi.org/10.23919/eusipco.2019.8902646","mag":"2983586762"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902646","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th 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/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031002666","display_name":"Aidan O. T. Hogg","orcid":"https://orcid.org/0000-0001-5501-7799"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aidan O. T. Hogg","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445125","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-9500-081X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065094891","display_name":"Amr H. Nour-Eldin","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Amr Nour-Eldin","raw_affiliation_strings":["Nuance Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8345,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74051981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.8502185344696045},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7401853799819946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6906179189682007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6693589091300964},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6233558058738708},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5725106000900269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019135475158691},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.462956964969635},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45644456148147583},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4327901601791382},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41266584396362305},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4105677306652069},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3783222734928131},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3558361232280731},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3196873664855957},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07324790954589844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07015293836593628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502185344696045},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7401853799819946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6906179189682007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6693589091300964},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6233558058738708},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5725106000900269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019135475158691},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.462956964969635},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45644456148147583},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4327901601791382},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41266584396362305},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4105677306652069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783222734928131},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3558361232280731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3196873664855957},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07324790954589844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07015293836593628},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco.2019.8902646","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/72098","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/72098","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference (EUSIPCO)","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1507423462","https://openalex.org/W1522301498","https://openalex.org/W1560838671","https://openalex.org/W1838748884","https://openalex.org/W1866989267","https://openalex.org/W1989364685","https://openalex.org/W1990269917","https://openalex.org/W1992272902","https://openalex.org/W2024483166","https://openalex.org/W2041638389","https://openalex.org/W2042336970","https://openalex.org/W2043429285","https://openalex.org/W2064675550","https://openalex.org/W2103253424","https://openalex.org/W2105854852","https://openalex.org/W2120979206","https://openalex.org/W2125114513","https://openalex.org/W2137075158","https://openalex.org/W2147817981","https://openalex.org/W2159373586","https://openalex.org/W2169936252","https://openalex.org/W2271406684","https://openalex.org/W2342810974","https://openalex.org/W2524375674","https://openalex.org/W2561217444","https://openalex.org/W2593239632","https://openalex.org/W2745644908","https://openalex.org/W2747368236","https://openalex.org/W2770597112","https://openalex.org/W2900024717","https://openalex.org/W2911394281","https://openalex.org/W2964121744","https://openalex.org/W3127686677","https://openalex.org/W4296927107","https://openalex.org/W6694336730","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2559040841","https://openalex.org/W1498240750","https://openalex.org/W2188451659","https://openalex.org/W2793383796","https://openalex.org/W3203878336","https://openalex.org/W2189089965","https://openalex.org/W2108273745","https://openalex.org/W2163541010","https://openalex.org/W2685907518","https://openalex.org/W3175075966"],"abstract_inverted_index":{"Estimating":[0],"the":[1,6,21,50,86,131,145],"quality":[2],"of":[3,8,54,72,103,142],"speech":[4,56,115],"without":[5],"use":[7],"a":[9,14,38,55,59,68,94,99],"clean":[10],"reference":[11],"signal":[12,57],"is":[13,65,111,117],"challenging":[15],"problem,":[16],"in":[17,58,77],"part":[18],"due":[19],"to":[20,26,48,119],"time":[22,61],"and":[23,116],"expense":[24],"required":[25],"collect":[27],"sufficient":[28],"training":[29],"data":[30],"for":[31,147],"modern":[32],"machine":[33],"learning":[34],"algorithms.":[35],"We":[36,83],"present":[37],"novel,":[39],"non-intrusive":[40],"estimator":[41],"that":[42,85],"exploits":[43],"recurrent":[44],"neural":[45,126],"network":[46,127],"architectures":[47],"predict":[49,91],"intrusive":[51],"POLQA":[52,92],"score":[53,141],"short":[60],"context.":[62],"The":[63,108,125],"predictor":[64],"based":[66],"on":[67,105],"novel":[69],"compressed":[70],"representation":[71],"modulation":[73],"domain":[74],"features,":[75],"used":[76],"conjunction":[78],"with":[79,93,137],"static":[80],"MFCC":[81],"features.":[82],"show":[84],"proposed":[87,109],"method":[88,110],"can":[89],"reliably":[90],"300":[95],"ms":[96],"context,":[97],"achieving":[98],"mean":[100,132],"absolute":[101],"error":[102],"0.21":[104],"unseen":[106,123],"data.":[107],"trained":[112],"using":[113],"English":[114],"shown":[118],"generalize":[120],"well":[121],"across":[122],"languages.":[124],"also":[128],"jointly":[129],"estimates":[130],"voice":[133],"activity":[134],"detection":[135],"(VAD)":[136],"an":[138,148],"F1":[139],"accuracy":[140],"0.9,":[143],"removing":[144],"need":[146],"external":[149],"VAD.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}