{"id":"https://openalex.org/W3197047457","doi":"https://doi.org/10.21437/interspeech.2021-1685","title":"Non-Intrusive Speech Quality Assessment with Transfer Learning and Subject-Specific Scaling","display_name":"Non-Intrusive Speech Quality Assessment with Transfer Learning and Subject-Specific Scaling","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197047457","doi":"https://doi.org/10.21437/interspeech.2021-1685","mag":"3197047457"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1685","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/296830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040722438","display_name":"Natalia Nessler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natalia Nessler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milos Cernak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107857636","display_name":"Paolo Prandoni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paolo Prandoni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008181078","display_name":"Pablo Mainar","orcid":"https://orcid.org/0009-0005-9662-492X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Mainar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6986,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84809533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2406","last_page":"2410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9786999821662903,"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":0.9307000041007996,"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":0.7320618629455566},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.649347186088562},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5934733152389526},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5865343809127808},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5052958130836487},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43377017974853516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4095805287361145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40824568271636963},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10190218687057495},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07681551575660706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7320618629455566},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.649347186088562},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5934733152389526},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5865343809127808},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5052958130836487},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43377017974853516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4095805287361145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40824568271636963},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10190218687057495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07681551575660706},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1685","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:296830","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/296830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:296830","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/296830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W2357926602","https://openalex.org/W2374569605","https://openalex.org/W2386062718","https://openalex.org/W899618282","https://openalex.org/W2386129765","https://openalex.org/W2368742525","https://openalex.org/W2364803570"],"abstract_inverted_index":{"In":[0,53],"communication":[1],"systems,":[2],"it":[3],"is":[4],"crucial":[5],"to":[6,48,87,103,158],"estimate":[7,104],"the":[8,33,49,83,89,105,108,141,155,180],"perceived":[9],"quality":[10],"of":[11,35,135],"audio":[12],"and":[13,25,78,138,173],"speech.":[14,193],"The":[15],"industrial":[16],"standards":[17],"for":[18,160,191],"many":[19],"years":[20],"have":[21,46],"been":[22],"PESQ,":[23,171],"3QUEST,":[24],"POLQA,":[26,172],"which":[27],"are":[28],"intrusive":[29],"methods.":[30],"This":[31],"restricts":[32],"possibilities":[34],"using":[36,131],"these":[37],"metrics":[38],"in":[39,111,119,154],"real-world":[40],"conditions,":[41],"where":[42],"we":[43,56,81,97,123,149],"might":[44],"not":[45],"access":[47],"clean":[50],"reference":[51],"signal.":[52],"this":[54],"work,":[55],"develop":[57],"a":[58,68,99,112,129,132,151],"new":[59,69],"non-intrusive":[60,113,175],"metric":[61],"based":[62],"on":[63,179],"crowd-sourced":[64],"data.":[65],"We":[66,115,185],"build":[67],"speech":[70,109],"dataset":[71,90],"by":[72,127],"combining":[73],"publicly":[74],"available":[75],"speech,":[76],"noises,":[77],"reverberations.":[79],"Then":[80],"follow":[82],"ITU":[84],"P.808":[85],"recommendation":[86],"label":[88],"with":[91,140],"mean":[92],"opinion":[93],"scores":[94,137,157,190],"(MOS).":[95],"Finally,":[96],"train":[98],"deep":[100],"neural":[101],"network":[102],"MOS":[106,156],"from":[107],"data":[110],"way.":[114],"propose":[116],"two":[117],"novelties":[118],"our":[120],"work.":[121],"First,":[122],"explore":[124],"transfer":[125],"learning":[126],"pre-training":[128],"model":[130,166],"larger":[133],"set":[134],"POLQA":[136,189],"finetuning":[139],"smaller":[142],"(and":[143],"thus":[144],"cheaper)":[145],"human-labeled":[146],"set.":[147,184],"Secondly,":[148],"perform":[150],"subject-specific":[152],"scaling":[153],"adjust":[159],"their":[161],"different":[162],"subjective":[163],"scales.":[164],"Our":[165],"yields":[167],"better":[168],"accuracy":[169],"than":[170],"other":[174],"methods":[176],"when":[177],"evaluated":[178],"independent":[181],"VCTK":[182],"test":[183],"also":[186],"report":[187],"misleading":[188],"reverberant":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
