{"id":"https://openalex.org/W4372266832","doi":"https://doi.org/10.1109/icassp49357.2023.10095132","title":"Efficient Speech Quality Assessment Using Self-Supervised Framewise Embeddings","display_name":"Efficient Speech Quality Assessment Using Self-Supervised Framewise Embeddings","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266832","doi":"https://doi.org/10.1109/icassp49357.2023.10095132"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://researchprofiles.ku.dk/da/publications/2db38fc9-f96d-413b-bf46-cd1d5e6e6798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032433720","display_name":"Karl El Hajal","orcid":"https://orcid.org/0000-0003-3128-335X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Karl El Hajal","raw_affiliation_strings":["&#x00C9;cole Polytechnique F&#x00E9;d&#x00E9;rale de Lausanne (EPFL),Lausanne,Switzerland"],"affiliations":[{"raw_affiliation_string":"&#x00C9;cole Polytechnique F&#x00E9;d&#x00E9;rale de Lausanne (EPFL),Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785514","display_name":"Zihan Wu","orcid":"https://orcid.org/0000-0003-2961-4615"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zihan Wu","raw_affiliation_strings":["&#x00C9;cole Polytechnique F&#x00E9;d&#x00E9;rale de Lausanne (EPFL),Lausanne,Switzerland"],"affiliations":[{"raw_affiliation_string":"&#x00C9;cole Polytechnique F&#x00E9;d&#x00E9;rale de Lausanne (EPFL),Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055084920","display_name":"Neil Scheidwasser","orcid":"https://orcid.org/0000-0001-9922-0289"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Neil Scheidwasser-Clow","raw_affiliation_strings":["University of Copenhagen,Copenhagen,Denmark","University of Copenhagen, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen,Copenhagen,Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008399208","display_name":"Gasser Elbanna","orcid":"https://orcid.org/0009-0002-2077-548X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Gasser Elbanna","raw_affiliation_strings":["&#x00C9;cole Polytechnique F&#x00E9;d&#x00E9;rale de Lausanne (EPFL),Lausanne,Switzerland","McGovern Institute for Brain Research MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"&#x00C9;cole Polytechnique F&#x00E9;d&#x00E9;rale de Lausanne (EPFL),Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"McGovern Institute for Brain Research MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491"},"institutions":[{"id":"https://openalex.org/I4210148785","display_name":"Logitech (Switzerland)","ror":"https://ror.org/05pkpss54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210148785"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Milos Cernak","raw_affiliation_strings":["Logitech Europe,Lausanne,Switzerland","Logitech Europe, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Logitech Europe,Lausanne,Switzerland","institution_ids":["https://openalex.org/I4210148785"]},{"raw_affiliation_string":"Logitech Europe, Lausanne, Switzerland","institution_ids":["https://openalex.org/I4210148785"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032433720"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.7686,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68959119,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.8264679312705994},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6630035638809204},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5481406450271606},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5154184103012085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5077544450759888},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4747258424758911},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4209528863430023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35583436489105225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32694071531295776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264679312705994},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6630035638809204},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5481406450271606},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5154184103012085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5077544450759888},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4747258424758911},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4209528863430023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35583436489105225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32694071531295776},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/2db38fc9-f96d-413b-bf46-cd1d5e6e6798","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/2db38fc9-f96d-413b-bf46-cd1d5e6e6798","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"El Hajal , K , Wu , Z , Scheidwasser-Clow , N , Elbanna , G & Cernak , M 2023 , Efficient Speech Quality Assessment Using Self-Supervised Framewise Embeddings . in Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing . IEEE , ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , vol. 2023-June , 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 , Rhodes Island , Greece , 04/06/2023 . https://doi.org/10.1109/ICASSP49357.2023.10095132","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/2db38fc9-f96d-413b-bf46-cd1d5e6e6798","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/2db38fc9-f96d-413b-bf46-cd1d5e6e6798","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"El Hajal , K , Wu , Z , Scheidwasser-Clow , N , Elbanna , G & Cernak , M 2023 , Efficient Speech Quality Assessment Using Self-Supervised Framewise Embeddings . in Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing . IEEE , ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , vol. 2023-June , 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 , Rhodes Island , Greece , 04/06/2023 . https://doi.org/10.1109/ICASSP49357.2023.10095132","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W349236604","https://openalex.org/W1795254317","https://openalex.org/W2593116425","https://openalex.org/W2922332774","https://openalex.org/W2939156090","https://openalex.org/W2963403924","https://openalex.org/W2987307811","https://openalex.org/W3035060554","https://openalex.org/W3036601975","https://openalex.org/W3095087462","https://openalex.org/W3160506022","https://openalex.org/W3163113319","https://openalex.org/W3196475561","https://openalex.org/W3197047457","https://openalex.org/W3198102247","https://openalex.org/W3200245256","https://openalex.org/W3201143670","https://openalex.org/W3201700775","https://openalex.org/W3202667537","https://openalex.org/W3213029956","https://openalex.org/W4206377423","https://openalex.org/W4214493665","https://openalex.org/W4221144124","https://openalex.org/W4221150524","https://openalex.org/W4226029093","https://openalex.org/W4283652729","https://openalex.org/W4296068997","https://openalex.org/W4296069122","https://openalex.org/W4296070197","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6790489232","https://openalex.org/W6800120440","https://openalex.org/W6801588699","https://openalex.org/W6803464654","https://openalex.org/W6804030475","https://openalex.org/W6809947431","https://openalex.org/W6810484339","https://openalex.org/W6838724896","https://openalex.org/W7073743773"],"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/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,10,26,123],"quality":[2,16,79,124],"assessment":[3],"is":[4,58],"essential":[5],"for":[6],"audio":[7],"researchers,":[8],"developers,":[9],"and":[11,14,74,112],"language":[12],"pathologists,":[13],"system":[15,41,57,88,96],"engineers.":[17],"The":[18,102],"current":[19],"state-of-the-art":[20],"systems":[21],"are":[22],"based":[23],"on":[24,89],"framewise":[25,107],"features":[27],"(hand-engineered":[28],"or":[29],"learnable)":[30],"combined":[31],"with":[32,42,116],"time":[33],"dependency":[34],"modeling.":[35],"This":[36],"paper":[37,103],"proposes":[38],"an":[39],"efficient":[40],"results":[43],"comparable":[44],"to":[45,98],"the":[46,51,87,94],"best":[47],"performing":[48],"model":[49],"in":[50],"ConferencingSpeech":[52],"2022":[53],"challenge.":[54],"Our":[55],"proposed":[56,95],"characterized":[59],"by":[60],"a":[61],"smaller":[62],"number":[63],"of":[64],"parameters":[65],"(40-60x),":[66],"fewer":[67],"FLOPS":[68],"(100x),":[69],"lower":[70,75],"memory":[71],"consumption":[72],"(10-15x),":[73],"latency":[76],"(30x).":[77],"Speech":[78],"practitioners":[80],"can":[81],"therefore":[82],"iterate":[83],"much":[84],"faster,":[85],"deploy":[86],"resource-limited":[90],"hardware,":[91],"and,":[92],"overall,":[93],"contributes":[97],"sustainable":[99],"machine":[100],"learning.":[101],"also":[104],"concludes":[105],"that":[106,113],"embeddings":[108,111],"outperform":[109],"utterance-level":[110],"multi-task":[114],"training":[115],"acoustic":[117],"conditions":[118],"modeling":[119],"does":[120],"not":[121],"degrade":[122],"prediction":[125],"while":[126],"providing":[127],"better":[128],"interpretation.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
