{"id":"https://openalex.org/W4297841726","doi":"https://doi.org/10.21437/interspeech.2022-10857","title":"CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment","display_name":"CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841726","doi":"https://doi.org/10.21437/interspeech.2022-10857"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10857","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10857","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.02577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100373052","display_name":"Yuchen Liu","orcid":"https://orcid.org/0000-0002-5376-0017"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]},{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Bose Corporation, USA","Department of Computer Science, Indiana University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068970053","display_name":"Li-Chia Yang","orcid":"https://orcid.org/0000-0001-7342-6529"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Chia Yang","raw_affiliation_strings":["Bose Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069386078","display_name":"Alexander D. Pawlicki","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Pawlicki","raw_affiliation_strings":["Bose Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028041356","display_name":"Marko Stamenovic","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marko Stamenovic","raw_affiliation_strings":["Bose Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3318","last_page":"3322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9918000102043152,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9918000102043152,"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/T10860","display_name":"Speech and Audio Processing","score":0.9878000020980835,"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":0.8017780780792236},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6718995571136475},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6210364699363708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5489020943641663},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5136589407920837},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.48405924439430237},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.43308985233306885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41388750076293945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3375777006149292},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10557329654693604},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.09916123747825623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017780780792236},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6718995571136475},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6210364699363708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5489020943641663},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5136589407920837},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.48405924439430237},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.43308985233306885},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41388750076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375777006149292},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10557329654693604},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.09916123747825623},{"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10857","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10857","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2211.02577","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.02577","pdf_url":"https://arxiv.org/pdf/2211.02577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.02577","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.02577","pdf_url":"https://arxiv.org/pdf/2211.02577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1437335841","https://openalex.org/W1561742478","https://openalex.org/W2125114513","https://openalex.org/W2141998673","https://openalex.org/W2142690424","https://openalex.org/W2291877678","https://openalex.org/W2557915412","https://openalex.org/W2735156122","https://openalex.org/W2939156090","https://openalex.org/W2939574508","https://openalex.org/W2963403924","https://openalex.org/W2963609956","https://openalex.org/W2972394484","https://openalex.org/W3028019732","https://openalex.org/W3040498734","https://openalex.org/W3097627357","https://openalex.org/W3105857760","https://openalex.org/W3161249751","https://openalex.org/W3196475561","https://openalex.org/W4226081178","https://openalex.org/W4229948754","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W3016124757","https://openalex.org/W3034520363","https://openalex.org/W2080843559","https://openalex.org/W2151415191"],"abstract_inverted_index":{"Speech":[0],"quality":[1,23,37,64,72],"assessment":[2,24,143],"has":[3],"been":[4],"a":[5,84],"critical":[6],"component":[7],"in":[8,47,61],"many":[9],"voice":[10],"communication":[11],"related":[12],"applications":[13],"such":[14],"as":[15,65],"telephony":[16],"and":[17,116,119,156],"online":[18],"conferencing.":[19],"Traditional":[20],"intrusive":[21],"speech":[22,63,76,142],"requires":[25],"the":[26,30,42,51,58,71,97,124,166,170],"clean":[27],"reference":[28],"of":[29,44,73,102],"degraded":[31,75],"utterance":[32],"to":[33,95,123,138,154,162,165],"provide":[34],"an":[35],"accurate":[36],"measurement.":[38],"This":[39],"requirement":[40],"limits":[41],"usability":[43],"these":[45],"methods":[46],"real-world":[48],"scenarios.":[49],"On":[50],"other":[52],"hand,":[53],"non-intrusive":[54,141],"subjective":[55],"measurement":[56],"is":[57],"``golden":[59],"standard\"":[60],"evaluating":[62],"human":[66,103],"listeners":[67],"can":[68],"intrinsically":[69],"evaluate":[70,106],"any":[74],"with":[77,145],"ease.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"propose":[83],"novel":[85],"end-to-end":[86],"model":[87,108,168],"structure":[88],"called":[89],"Convolutional":[90],"Context-Aware":[91],"Transformer":[92],"(CCAT)":[93],"network":[94],"predict":[96],"mean":[98],"opinion":[99],"score":[100],"(MOS)":[101],"raters.":[104],"We":[105],"our":[107,121],"on":[109,169],"three":[110],"MOS-annotated":[111],"datasets":[112],"spanning":[113],"multiple":[114],"languages":[115],"distortion":[117],"types":[118],"submit":[120],"results":[122],"ConferencingSpeech":[125],"2022":[126],"Challenge.":[127],"Our":[128],"experiments":[129],"show":[130],"that":[131],"CCAT":[132],"provides":[133],"promising":[134],"MOS":[135],"predictions":[136],"compared":[137,164],"current":[139],"state-of-art":[140],"models":[144],"average":[146,157],"Pearson":[147],"correlation":[148],"coefficient":[149],"(PCC)":[150],"increasing":[151],"from":[152,160],"0.530":[153],"0.697":[155],"RMSE":[158],"decreasing":[159],"0.768":[161],"0.570":[163],"baseline":[167],"challenge":[171],"evaluation":[172],"test":[173],"set.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}