{"id":"https://openalex.org/W2938881288","doi":"https://doi.org/10.1109/icassp.2019.8682754","title":"Improving Deep Models of Speech Quality Prediction through Voice Activity Detection and Entropy-based Measures","display_name":"Improving Deep Models of Speech Quality Prediction through Voice Activity Detection and Entropy-based Measures","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938881288","doi":"https://doi.org/10.1109/icassp.2019.8682754","mag":"2938881288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5011528026","display_name":"Jasper Ooster","orcid":"https://orcid.org/0000-0003-1498-3776"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]},{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jasper Ooster","raw_affiliation_strings":["Medizinische Physik and Cluster of Excellence Hearing4all, Carl von Ossietzky Universit\u00e4t, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Medizinische Physik and Cluster of Excellence Hearing4all, Carl von Ossietzky Universit\u00e4t, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]},{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":["Medizinische Physik and Cluster of Excellence Hearing4all, Carl von Ossietzky Universit\u00e4t, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Medizinische Physik and Cluster of Excellence Hearing4all, Carl von Ossietzky Universit\u00e4t, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011528026"],"corresponding_institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":2.9854,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91947956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"640"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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":0.6573803424835205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6451854109764099},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6000464558601379},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5267740488052368},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.49506059288978577},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4881158769130707},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4686664342880249},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4608973562717438},{"id":"https://openalex.org/keywords/predictive-power","display_name":"Predictive power","score":0.444375216960907},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.44252121448516846},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.43028199672698975},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38902121782302856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37000730633735657},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11920872330665588},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11414265632629395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0829523503780365}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6573803424835205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6451854109764099},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6000464558601379},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5267740488052368},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.49506059288978577},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4881158769130707},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4686664342880249},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4608973562717438},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.444375216960907},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44252121448516846},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.43028199672698975},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38902121782302856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37000730633735657},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11920872330665588},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11414265632629395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0829523503780365},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1594031697","https://openalex.org/W1795254317","https://openalex.org/W1989351718","https://openalex.org/W2043429285","https://openalex.org/W2048741136","https://openalex.org/W2125114513","https://openalex.org/W2151484683","https://openalex.org/W2153038597","https://openalex.org/W2397147568","https://openalex.org/W2587464121","https://openalex.org/W2778517680","https://openalex.org/W2889128201","https://openalex.org/W2895866335","https://openalex.org/W3085162807"],"related_works":["https://openalex.org/W3164858600","https://openalex.org/W3109498233","https://openalex.org/W2031768607","https://openalex.org/W4200068392","https://openalex.org/W4297798732","https://openalex.org/W4205278983","https://openalex.org/W2550171623","https://openalex.org/W596245619","https://openalex.org/W3161890269","https://openalex.org/W4298324454"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"Deep":[3],"machine":[4],"listening":[5],"for":[6,125],"Estimating":[7],"Speech":[8],"Quality":[9],"(DESQ),":[10],"which":[11,140],"predicts":[12],"the":[13,35,43,60,78,90,110,126,128],"perceived":[14],"speech":[15,52,61],"quality":[16],"based":[17],"on":[18,59,77],"phoneme":[19],"posterior":[20],"probabilities":[21],"obtained":[22],"from":[23,132],"a":[24,56,66,72,121],"deep":[25],"neural":[26],"network.":[27],"The":[28,84],"degradation":[29],"of":[30,81,98],"phonemes":[31],"is":[32,40,86,141],"quantified":[33],"with":[34],"entropy-based":[36],"Gini":[37],"measure":[38,112],"that":[39],"compared":[41],"to":[42,136],"mean":[44,94],"temporal":[45],"distance":[46],"(MTD)":[47],"proposed":[48],"earlier.":[49],"Since":[50],"long":[51],"pauses":[53],"might":[54],"have":[55],"large":[57],"effect":[58,76],"quality,":[62],"we":[63],"investigate":[64],"if":[65],"voice":[67],"activity":[68],"detection":[69],"(VAD)":[70],"has":[71],"beneficial":[73],"or":[74],"detrimental":[75],"predictive":[79],"power":[80],"our":[82],"model.":[83],"evaluation":[85],"performed":[87],"by":[88,105],"correlating":[89],"model":[91],"output":[92],"and":[93,113,149],"opinion":[95],"scores":[96],"(MOS)":[97],"normal-hearing":[99],"listeners":[100],"who":[101],"rated":[102],"signals":[103],"degraded":[104],"typical":[106],"VoIP":[107],"artifacts.":[108],"While":[109],"Gini-based":[111],"MTD":[114],"result":[115],"in":[116],"very":[117],"similar":[118],"predictions":[119],"(with":[120],"lower":[122],"computational":[123],"cost":[124],"Gini-measure),":[127],"VAD":[129],"increases":[130],"performance":[131],"r":[133,137],"=":[134,138],"0.87":[135],"0.91":[139],"higher":[142],"than":[143],"three":[144],"competing":[145],"baselines":[146],"(ITU-P.563,":[147],"ANIQUE+,":[148],"SRM-Rnorm).":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}