{"id":"https://openalex.org/W3117722298","doi":"https://doi.org/10.23919/eusipco47968.2020.9287785","title":"Non-Intrusive Estimation of Speech Signal Parameters using a Frame-based Machine Learning Approach","display_name":"Non-Intrusive Estimation of Speech Signal Parameters using a Frame-based Machine Learning Approach","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3117722298","doi":"https://doi.org/10.23919/eusipco47968.2020.9287785","mag":"3117722298"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287785","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th 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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102383739","display_name":"Lucia Berger","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":"Lucia Berger","raw_affiliation_strings":["Nuance Communications Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077676839","display_name":"Carl Quillen","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":"Carl Quillen","raw_affiliation_strings":["Nuance Communications Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc","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":["Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2166,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80387425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"450"},"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":0.9993000030517578,"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":0.9984999895095825,"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/pesq","display_name":"PESQ","score":0.9653809070587158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.707931637763977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6752967834472656},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5590695142745972},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5394779443740845},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5188809037208557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5175961256027222},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5078852772712708},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49306270480155945},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.48328784108161926},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48098909854888916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47032463550567627},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4490351676940918},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42502880096435547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42001429200172424},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4133647680282593},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4125213623046875},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.29041001200675964},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2314666211605072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17615589499473572},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1228795051574707},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08835181593894958},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08363834023475647}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9653809070587158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707931637763977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6752967834472656},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5590695142745972},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5394779443740845},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5188809037208557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5175961256027222},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5078852772712708},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49306270480155945},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.48328784108161926},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48098909854888916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47032463550567627},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4490351676940918},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42502880096435547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42001429200172424},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4133647680282593},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4125213623046875},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.29041001200675964},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2314666211605072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17615589499473572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1228795051574707},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08835181593894958},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08363834023475647},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287785","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W4416539","https://openalex.org/W1507423462","https://openalex.org/W1522301498","https://openalex.org/W1598201010","https://openalex.org/W2024483166","https://openalex.org/W2064675550","https://openalex.org/W2117678320","https://openalex.org/W2129070077","https://openalex.org/W2159969054","https://openalex.org/W2180309746","https://openalex.org/W2296434735","https://openalex.org/W2342810974","https://openalex.org/W2410879554","https://openalex.org/W2519091744","https://openalex.org/W2539238457","https://openalex.org/W2627010112","https://openalex.org/W2747368236","https://openalex.org/W2765649928","https://openalex.org/W2900429685","https://openalex.org/W2902922150","https://openalex.org/W2911394281","https://openalex.org/W2914312680","https://openalex.org/W2922332774","https://openalex.org/W2936774411","https://openalex.org/W2949382160","https://openalex.org/W2962780374","https://openalex.org/W2962808638","https://openalex.org/W2964121744","https://openalex.org/W2973157397","https://openalex.org/W2983586762","https://openalex.org/W2990118552","https://openalex.org/W4289232656","https://openalex.org/W4296927107","https://openalex.org/W4298152313","https://openalex.org/W6631190155","https://openalex.org/W6679097437","https://openalex.org/W6694991879","https://openalex.org/W6756345725","https://openalex.org/W6906815279"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"We":[0,27,58],"present":[1],"a":[2,24,61,78,87,132,180],"novel,":[3],"non-intrusive":[4],"method":[5,178],"that":[6,51,60,168],"jointly":[7],"estimates":[8],"acoustic":[9,153],"signal":[10],"properties":[11],"associated":[12],"with":[13,55,156,186],"the":[14,47,107,142,169,189],"perceptual":[15],"speech":[16,25],"quality,":[17],"level":[18],"of":[19,34,42,65,91,122,152,161],"reverberation":[20],"and":[21,39,45,101,165,173],"noise":[22],"in":[23,49,159],"signal.":[26],"explore":[28],"various":[29],"machine":[30],"learning":[31],"frameworks,":[32],"consisting":[33,64],"popular":[35],"feature":[36,71],"extraction":[37],"front-ends":[38],"two":[40],"types":[41],"regression":[43],"models":[44],"show":[46,59,148,167],"trade-off":[48],"performance":[50,158],"must":[52],"be":[53],"considered":[54],"each":[56,150],"combination.":[57],"short-time":[62],"framework":[63],"an":[66,119],"80-dimension":[67],"log-Mel":[68],"filter":[69],"bank":[70],"front-end":[72],"employing":[73],"spectral":[74],"augmentation,":[75],"followed":[76],"by":[77],"3":[79],"layer":[80],"LSTM":[81],"recurrent":[82],"neural":[83],"network":[84],"model":[85],"achieves":[86,118,131],"mean":[88,135],"absolute":[89,136],"error":[90,137],"3.3":[92],"dB":[93,97,134],"for":[94,98,103,115,138],"C50,":[95,171],"2.3":[96],"segmental":[99],"SNR":[100,172],"0.3":[102],"PESQ":[104,174],"estimation":[105,140],"on":[106,124,141,188],"Libri":[108],"Augmented":[109],"(LA)":[110],"database.":[111],"The":[112,127],"internal":[113],"VAD":[114],"this":[116,125],"system":[117,129],"F1":[120],"score":[121],"0.93":[123],"data.":[126],"proposed":[128,177],"also":[130],"2.4":[133],"C50":[139],"ACE":[143],"test":[144,191],"set.":[145,192],"Furthermore,":[146],"we":[147],"how":[149],"type":[151],"parameter":[154],"correlates":[155],"ASR":[157],"terms":[160],"ground":[162],"truth":[163],"labels":[164],"additionally":[166],"estimated":[170],"from":[175],"our":[176],"have":[179],"high":[181],"correlation":[182],"(greater":[183],"than":[184],"0.92)":[185],"WER":[187],"LA":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}