{"id":"https://openalex.org/W3152626170","doi":"https://doi.org/10.21437/interspeech.2021-299","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","display_name":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3152626170","doi":"https://doi.org/10.21437/interspeech.2021-299","mag":"3152626170"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-299","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-299","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.09494","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069979525","display_name":"Gabriel Mittag","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gabriel Mittag","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069905492","display_name":"Babak Naderi","orcid":"https://orcid.org/0009-0006-4778-5417"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Babak Naderi","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061879146","display_name":"Assmaa Chehadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assmaa Chehadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075001284","display_name":"Sebastian M\u00f6ller","orcid":"https://orcid.org/0000-0003-3057-0760"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian M\u00f6ller","raw_affiliation_strings":["Technical University of Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2127","last_page":"2131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7900009155273438},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7895523905754089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5423946380615234},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.534838855266571},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5145315527915955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43417567014694214},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.41651225090026855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34075677394866943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900009155273438},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7895523905754089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5423946380615234},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.534838855266571},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5145315527915955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43417567014694214},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.41651225090026855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34075677394866943},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":4,"locations":[{"id":"doi:10.21437/interspeech.2021-299","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-299","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:arXiv.org:2104.09494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.09494","pdf_url":"https://arxiv.org/pdf/2104.09494","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"},{"id":"mag:3152626170","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.09494.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.09494","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.09494","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.09494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.09494","pdf_url":"https://arxiv.org/pdf/2104.09494","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":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W652928785","https://openalex.org/W1552853484","https://openalex.org/W1849775568","https://openalex.org/W1969653274","https://openalex.org/W1976320170","https://openalex.org/W1983108229","https://openalex.org/W2043429285","https://openalex.org/W2405478093","https://openalex.org/W2486436843","https://openalex.org/W2593116425","https://openalex.org/W2807366589","https://openalex.org/W2922332774","https://openalex.org/W2939156090","https://openalex.org/W2944426940","https://openalex.org/W2963403868","https://openalex.org/W2963403924","https://openalex.org/W2972419867","https://openalex.org/W3015545615","https://openalex.org/W3015644200","https://openalex.org/W3025844872","https://openalex.org/W3032558098","https://openalex.org/W3037038648","https://openalex.org/W3090098535","https://openalex.org/W3097206152","https://openalex.org/W3097787598","https://openalex.org/W3097906045","https://openalex.org/W3176511914"],"related_works":["https://openalex.org/W3196475561","https://openalex.org/W2778517680","https://openalex.org/W3164201234","https://openalex.org/W3013796469","https://openalex.org/W3128680834","https://openalex.org/W2994785103","https://openalex.org/W2990118552","https://openalex.org/W2808405016","https://openalex.org/W3208029485","https://openalex.org/W3003231992","https://openalex.org/W2974831423","https://openalex.org/W1820524266","https://openalex.org/W2905699315","https://openalex.org/W3184815887","https://openalex.org/W3206116612","https://openalex.org/W2555047121","https://openalex.org/W2936399153","https://openalex.org/W2765507192","https://openalex.org/W3144810982","https://openalex.org/W3026827614"],"abstract_inverted_index":{"In":[0,24],"this":[1,67],"paper,":[2],"we":[3],"present":[4],"an":[5],"update":[6],"to":[7,26,128],"the":[8,27,30,36,51,55,73,94],"NISQA":[9,115],"speech":[10,49,57,85,135],"quality":[11,58,77],"prediction":[12],"model":[13,31,52,97,139],"that":[14,19,107],"is":[15,32,41],"focused":[16],"on":[17,101,120],"distortions":[18],"occur":[20],"in":[21,66],"communication":[22],"networks.":[23],"contrast":[25],"previous":[28],"version,":[29],"trained":[33,117],"end-to-end":[34],"and":[35,39,63,65,91,118,126,141],"time-dependency":[37],"modelling":[38],"time-pooling":[40],"achieved":[42],"through":[43],"a":[44,76,102],"Self-Attention":[45],"mechanism.":[46],"Besides":[47],"overall":[48],"quality,":[50],"also":[53,132],"predicts":[54],"four":[56],"dimensions":[59],"Noisiness,":[60],"Coloration,":[61],"Discontinuity,":[62],"Loudness,":[64],"way":[68],"gives":[69],"more":[70],"insight":[71],"into":[72],"cause":[74],"of":[75,93,110],"degradation.":[78],"Furthermore,":[79],"new":[80],"datasets":[81,122,142],"with":[82],"over":[83],"13,000":[84],"files":[86],"were":[87],"created":[88],"for":[89,133],"training":[90],"validation":[92],"model.":[95],"The":[96,137],"was":[98,116],"finally":[99],"tested":[100],"new,":[103],"live-talking":[104],"test":[105],"dataset":[106],"contains":[108],"recordings":[109],"real":[111],"telephone":[112],"calls.":[113],"Overall,":[114],"evaluated":[119],"81":[121],"from":[123],"different":[124],"sources":[125],"showed":[127],"provide":[129],"reliable":[130],"predictions":[131],"unknown":[134],"samples.":[136],"code,":[138],"weights,":[140],"are":[143],"open-sourced.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}