{"id":"https://openalex.org/W3094748844","doi":"https://doi.org/10.21437/interspeech.2020-1740","title":"End-to-End Speech Intelligibility Prediction Using Time-Domain Fully Convolutional Neural Networks","display_name":"End-to-End Speech Intelligibility Prediction Using Time-Domain Fully Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094748844","doi":"https://doi.org/10.21437/interspeech.2020-1740","mag":"3094748844"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/34806093-aeca-46db-8133-f49202c5d6a9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055309051","display_name":"Mathias Bach Pedersen","orcid":"https://orcid.org/0000-0002-5897-054X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Mathias B. Pedersen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006420917","display_name":"Morten Kolb\u00e6k","orcid":"https://orcid.org/0000-0002-2561-4960"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Morten Kolb\u00e6k","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061115495","display_name":"Asger Heidemann Andersen","orcid":"https://orcid.org/0000-0001-6111-0084"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Asger H. Andersen","raw_affiliation_strings":["Oticon A/S, Denmark"],"affiliations":[{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103115969","display_name":"S\u00f8ren Holdt Jensen","orcid":"https://orcid.org/0000-0002-1050-470X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"S\u00f8ren H. Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]},{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Oticon A/S, Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055309051"],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":1.6669,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8475971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1151","last_page":"1155"},"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":0.9993000030517578,"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":0.9976000189781189,"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":0.7527617812156677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6715868711471558},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6006393432617188},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5233437418937683},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4782751500606537},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4133566617965698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3521110713481903},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.091024249792099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527617812156677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6715868711471558},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6006393432617188},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5233437418937683},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4782751500606537},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4133566617965698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521110713481903},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.091024249792099},{"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":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/34806093-aeca-46db-8133-f49202c5d6a9","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/34806093-aeca-46db-8133-f49202c5d6a9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pedersen, M, Kolb\u00e6k, M, Andersen, A H, Jensen, S H & Jensen, J 2020, End-to-end Speech Intelligibility Prediction Using Time-Domain Fully Convolutional Neural Networks. in INTERSPEECH 2020. Proceedings of the International Conference on Spoken Language Processing, pp. 1151-1155, Interspeech 2020, Shanghai, China, 25/10/2020. https://doi.org/10.21437/Interspeech.2020-1740","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/34806093-aeca-46db-8133-f49202c5d6a9","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/34806093-aeca-46db-8133-f49202c5d6a9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pedersen, M, Kolb\u00e6k, M, Andersen, A H, Jensen, S H & Jensen, J 2020, End-to-end Speech Intelligibility Prediction Using Time-Domain Fully Convolutional Neural Networks. in INTERSPEECH 2020. Proceedings of the International Conference on Spoken Language Processing, pp. 1151-1155, Interspeech 2020, Shanghai, China, 25/10/2020. https://doi.org/10.21437/Interspeech.2020-1740","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1893876709","https://openalex.org/W1901129140","https://openalex.org/W1991906437","https://openalex.org/W2078528584","https://openalex.org/W2085191029","https://openalex.org/W2087126002","https://openalex.org/W2092644348","https://openalex.org/W2128631678","https://openalex.org/W2141998673","https://openalex.org/W2153038597","https://openalex.org/W2342810974","https://openalex.org/W2395763495","https://openalex.org/W2465704452","https://openalex.org/W2516001803","https://openalex.org/W2550397165","https://openalex.org/W2782607396","https://openalex.org/W2809874909","https://openalex.org/W2889174214","https://openalex.org/W2889830381","https://openalex.org/W2898446161","https://openalex.org/W2943554574","https://openalex.org/W2945449954","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W3098606562","https://openalex.org/W3103840368","https://openalex.org/W4234750057"],"related_works":["https://openalex.org/W4391621807","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391621790","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Data-driven":[0],"speech":[1,12],"intelligibility":[2,13,56],"prediction":[3],"has":[4],"been":[5],"slow":[6],"totake":[7],"off.":[8],"Datasets":[9],"of":[10,57,80],"measured":[11],"are":[14,19,34],"scarce,and":[15],"so":[16],"current":[17],"models":[18],"relatively":[20],"small":[21],"and":[22,32,49,69],"rely":[23],"on":[24,30,51],"hand-picked":[25],"features.":[26],"Classical":[27],"predictors":[28,73],"based":[29],"psychoacousticmodels":[31],"heuristics":[33],"still":[35],"the":[36,90],"state-of-the-art.":[37],"This":[38],"workproposes":[39],"a":[40,64],"U-Net":[41],"inspired":[42],"fully":[43],"convolutional":[44],"neural":[45],"networkarchitecture,":[46],"NSIP,":[47],"trained":[48],"tested":[50],"ten":[52],"datasets":[53,95],"to":[54,63,84,99],"pre-dict":[55],"time-domain":[58],"speech.":[59],"The":[60,78],"architecture":[61],"iscompared":[62],"frequency":[65],"domain":[66],"data-driven":[67],"predictor":[68],"tothe":[70],"classical":[71,100],"state-of-the-art":[72],"STOI,":[74],"ESTOI,":[75],"HASPIand":[76],"SIIB.":[77],"performance":[79,97],"NSIP":[81],"is":[82],"found":[83],"be":[85],"superior":[86],"fordatasets":[87],"seen":[88],"in":[89],"training":[91],"phase.":[92],"On":[93],"unseen":[94],"NSIPreaches":[96],"comparable":[98],"predictors.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
