{"id":"https://openalex.org/W4307298605","doi":"https://doi.org/10.1007/s10772-022-10011-y","title":"Non-intrusive speech quality assessment using context-aware neural networks","display_name":"Non-intrusive speech quality assessment using context-aware neural networks","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4307298605","doi":"https://doi.org/10.1007/s10772-022-10011-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-022-10011-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-022-10011-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-022-10011-y.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10772-022-10011-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050008382","display_name":"Rahul Kumar Jaiswal","orcid":"https://orcid.org/0000-0003-3800-7235"},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Rahul Kumar Jaiswal","raw_affiliation_strings":["Department of Information and Communication Technology, Faculty of Engineering and Science, University of Agder, Grimstad, Norway"],"raw_orcid":"https://orcid.org/0000-0003-3800-7235","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technology, Faculty of Engineering and Science, University of Agder, Grimstad, Norway","institution_ids":["https://openalex.org/I200650556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002172554","display_name":"Rajesh Kumar Dubey","orcid":"https://orcid.org/0000-0003-0028-507X"},"institutions":[{"id":"https://openalex.org/I4210133503","display_name":"Central University of Haryana","ror":"https://ror.org/03mtwkv54","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210133503"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajesh Kumar Dubey","raw_affiliation_strings":["Department of Electrical Engineering, School of Engineering and Technology, Central University of Haryana, Mahendergarh, India"],"raw_orcid":"https://orcid.org/0000-0003-0028-507X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, School of Engineering and Technology, Central University of Haryana, Mahendergarh, India","institution_ids":["https://openalex.org/I4210133503"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050008382"],"corresponding_institution_ids":["https://openalex.org/I200650556"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2780},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2780},"fwci":0.2976,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51851234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"25","issue":"4","first_page":"947","last_page":"965"},"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":0.9965000152587891,"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":0.9965000152587891,"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":0.8885298371315002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.68101966381073},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6592196226119995},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6255819797515869},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5329362750053406},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5230235457420349},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5024616718292236},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4878399670124054},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47671598196029663},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.46912360191345215},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.45898187160491943},{"id":"https://openalex.org/keywords/voice-over-ip","display_name":"Voice over IP","score":0.45507705211639404},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4430193305015564},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.43469586968421936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41979777812957764},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.32323992252349854},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.23671263456344604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885298371315002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.68101966381073},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6592196226119995},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6255819797515869},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5329362750053406},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5230235457420349},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5024616718292236},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4878399670124054},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47671598196029663},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.46912360191345215},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.45898187160491943},{"id":"https://openalex.org/C171246234","wikidata":"https://www.wikidata.org/wiki/Q81945","display_name":"Voice over IP","level":3,"score":0.45507705211639404},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4430193305015564},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43469586968421936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41979777812957764},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.32323992252349854},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.23671263456344604},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":2,"locations":[{"id":"doi:10.1007/s10772-022-10011-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-022-10011-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-022-10011-y.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},{"id":"pmh:oai:uia.brage.unit.no:11250/3064461","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/3064461","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"947\u2013965","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.1007/s10772-022-10011-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-022-10011-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-022-10011-y.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327751","display_name":"Universitetet i Agder","ror":"https://ror.org/03x297z98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307298605.pdf","grobid_xml":"https://content.openalex.org/works/W4307298605.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1532289440","https://openalex.org/W1533861849","https://openalex.org/W1552314771","https://openalex.org/W1563939609","https://openalex.org/W1593029225","https://openalex.org/W1678356000","https://openalex.org/W1849775568","https://openalex.org/W1879998264","https://openalex.org/W1989351718","https://openalex.org/W1990269917","https://openalex.org/W2043429285","https://openalex.org/W2051057783","https://openalex.org/W2095705004","https://openalex.org/W2105854852","https://openalex.org/W2107601051","https://openalex.org/W2109349638","https://openalex.org/W2116668371","https://openalex.org/W2125114513","https://openalex.org/W2126554103","https://openalex.org/W2128402994","https://openalex.org/W2130813098","https://openalex.org/W2132444544","https://openalex.org/W2140651276","https://openalex.org/W2144351953","https://openalex.org/W2144404214","https://openalex.org/W2145760110","https://openalex.org/W2151484683","https://openalex.org/W2153894152","https://openalex.org/W2169534040","https://openalex.org/W2295598076","https://openalex.org/W2342810974","https://openalex.org/W2492746552","https://openalex.org/W2501398076","https://openalex.org/W2547634885","https://openalex.org/W2560747691","https://openalex.org/W2593239632","https://openalex.org/W2611743072","https://openalex.org/W2724494584","https://openalex.org/W2742201964","https://openalex.org/W2791846162","https://openalex.org/W2803258749","https://openalex.org/W2844392751","https://openalex.org/W2887481643","https://openalex.org/W2888520991","https://openalex.org/W2889128201","https://openalex.org/W2914046102","https://openalex.org/W2918342144","https://openalex.org/W2922332774","https://openalex.org/W2929602570","https://openalex.org/W2962964572","https://openalex.org/W2963190722","https://openalex.org/W2963403924","https://openalex.org/W2964021722","https://openalex.org/W2980169064","https://openalex.org/W3001387854","https://openalex.org/W3015644200","https://openalex.org/W3037038648","https://openalex.org/W3080622597","https://openalex.org/W3081586209","https://openalex.org/W3134002425","https://openalex.org/W3147539069","https://openalex.org/W3152199044","https://openalex.org/W4211118001","https://openalex.org/W4232801258","https://openalex.org/W4239751208","https://openalex.org/W4243367342","https://openalex.org/W6631190155","https://openalex.org/W6637730093","https://openalex.org/W6674385629","https://openalex.org/W6757107679","https://openalex.org/W7056108541"],"related_works":["https://openalex.org/W2168417340","https://openalex.org/W2118159520","https://openalex.org/W1998521395","https://openalex.org/W2144314030","https://openalex.org/W2109051065","https://openalex.org/W2571917423","https://openalex.org/W2020464095","https://openalex.org/W3035123403","https://openalex.org/W30434212","https://openalex.org/W1540787848"],"abstract_inverted_index":{"Abstract":[0],"To":[1,94],"meet":[2],"the":[3,53,59,70,113,118,150,179,188,198,202,211,214],"human":[4],"perceived":[5],"quality":[6,32,60,77,91,104,137,156,221],"of":[7,48,61,72,85,117,173,190,193],"experience":[8],"(QoE)":[9],"while":[10],"communicating":[11],"over":[12,15],"various":[13],"Voice":[14],"Internet":[16],"protocol":[17],"(VoIP)":[18],"applications,":[19],"for":[20,144],"example":[21],"Google":[22],"Meet,":[23],"Microsoft":[24],"Skype,":[25],"Apple":[26],"FaceTime,":[27],"etc.":[28],"a":[29,100,128],"precise":[30],"speech":[31,62,76,90,103,122,136,155,162,167,181,194,200,220],"assessment":[33,105],"metric":[34,38,78,106,204,212],"is":[35,67,124],"needed.":[36],"The":[37,160],"should":[39],"be":[40],"able":[41],"to":[42,148,210],"detect":[43],"and":[44,57,142],"segregate":[45],"different":[46,83,171,207],"types":[47,84,172],"noise":[49,86,114,146,151],"degradations":[50,87],"present":[51],"in":[52,63,111,187,206],"surroundings":[54],"before":[55,88,219],"measuring":[56],"monitoring":[58],"real-time.":[64],"Our":[65],"research":[66],"motivated":[68],"by":[69,170],"lack":[71],"clear":[73],"evidence":[74],"presenting":[75],"that":[79,95,164,185],"can":[80],"firstly":[81],"distinguish":[82],"providing":[89],"prediction":[92],"decision.":[93],"end,":[96],"this":[97],"paper":[98],"presents":[99],"novel":[101],"non-intrusive":[102],"using":[107,127],"context-aware":[108],"neural":[109],"networks":[110,133],"which":[112],"class":[115,147],"(context)":[116],"degraded":[119,169],"or":[120],"noisy":[121,161],"signal":[123],"first":[125],"identified":[126],"classifier":[129],"then":[130],"deep":[131],"neutral":[132],"(DNNs)":[134],"based":[135],"metrics":[138],"(SQMs)":[139],"are":[140,176,216],"trained":[141],"optimized":[143,154],"each":[145],"obtain":[149],"class-specific":[152],"(context-specific)":[153],"predictions":[157],"(MOS":[158],"scores).":[159],"signals,":[163],"is,":[165],"clean":[166],"signals":[168],"background":[174],"noises":[175],"taken":[177],"from":[178,197],"NOIZEUS":[180,199],"corpus.":[182],"Results":[183],"demonstrate":[184],"even":[186],"presence":[189],"less":[191],"number":[192],"samples":[195],"available":[196],"corpus,":[201],"proposed":[203],"outperforms":[205],"contexts":[208,215],"compared":[209],"where":[213],"not":[217],"classified":[218],"prediction.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
