{"id":"https://openalex.org/W4402111656","doi":"https://doi.org/10.21437/interspeech.2024-1421","title":"No-Reference Speech Intelligibility Prediction Leveraging a Noisy-Speech ASR Pre-Trained Model","display_name":"No-Reference Speech Intelligibility Prediction Leveraging a Noisy-Speech ASR Pre-Trained Model","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111656","doi":"https://doi.org/10.21437/interspeech.2024-1421"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1421","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/ws/files/771035182/wang24y_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081906674","display_name":"Haolan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haolan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051158946","display_name":"Amin Edraki","orcid":"https://orcid.org/0000-0002-0843-5522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amin Edraki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101683153","display_name":"Wai-Yip Chan","orcid":"https://orcid.org/0000-0001-5322-2449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai-Yip Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048592470","display_name":"Iv\u00e1n L\u00f3pez\u2010Espejo","orcid":"https://orcid.org/0000-0001-8634-7897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iv\u00e1n L\u00f3pez-Espejo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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/I4210091381","display_name":"William Demant Holding (Denmark)","ror":"https://ror.org/00an7pj80","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210091381"]},{"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":"Jesper Jensen","raw_affiliation_strings":["Aalborg University, The Technical Faculty of IT and Design, DK","Demant A/S, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Demant A/S, DK","institution_ids":["https://openalex.org/I4210091381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2825,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61744327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3849","last_page":"3853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9983000159263611,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8435914516448975},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7235269546508789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7024254202842712},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5688464641571045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4423699378967285},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.422625869512558},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4180675745010376},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18516889214515686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435914516448975},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7235269546508789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7024254202842712},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5688464641571045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4423699378967285},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.422625869512558},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4180675745010376},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18516889214515686},{"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.2024-1421","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/3d7d37f2-cd9b-4447-a607-86fbd6768d94","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/3d7d37f2-cd9b-4447-a607-86fbd6768d94","pdf_url":"https://vbn.aau.dk/ws/files/771035182/wang24y_interspeech.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, H, Edraki, A, Chan, W Y, L\u00f3pez-Espejo, I & Jensen, J 2024, No-Reference Speech Intelligibility Prediction Leveraging a Noisy-Speech ASR Pre-Trained Model. in Interspeech 2024. International Speech Communications Association, Proceedings of the International Conference on Spoken Language Processing, pp. 3849-3853, INTERSPEECH 2024, Kos Island, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1421","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/3d7d37f2-cd9b-4447-a607-86fbd6768d94","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/3d7d37f2-cd9b-4447-a607-86fbd6768d94","pdf_url":"https://vbn.aau.dk/ws/files/771035182/wang24y_interspeech.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, H, Edraki, A, Chan, W Y, L\u00f3pez-Espejo, I & Jensen, J 2024, No-Reference Speech Intelligibility Prediction Leveraging a Noisy-Speech ASR Pre-Trained Model. in Interspeech 2024. International Speech Communications Association, Proceedings of the International Conference on Spoken Language Processing, pp. 3849-3853, INTERSPEECH 2024, Kos Island, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1421","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320331522","display_name":"William Demant Fonden","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111656.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W3151937861","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"deep":[3],"learning":[4],"have":[5],"improved":[6],"the":[7,17,24],"capabilities":[8],"of":[9,19,26,34,75,96],"data-driven":[10,27],"speech":[11,20,50],"intelligibility":[12,21],"prediction":[13],"(SIP)":[14],"algorithms.":[15,28],"Nevertheless,":[16],"scarcity":[18],"datasets":[22,97],"limits":[23],"development":[25],"This":[29],"study":[30],"introduces":[31],"a":[32,39,57,72,88,94],"set":[33],"no-reference":[35,64],"SIP":[36,65,91],"algorithms":[37,66],"leveraging":[38],"pre-trained":[40],"wav2vec":[41,46],"2.0":[42,47],"backbone.":[43],"We":[44,62],"adapt":[45],"for":[48],"automatic":[49],"recognition":[51],"under":[52],"additive":[53],"noise":[54],"conditions":[55],"with":[56,68],"parameter-efficient":[58],"methodology,":[59],"low-rank":[60],"adaptation.":[61],"demonstrate":[63],"designed":[67],"this":[69],"approach":[70],"using":[71],"moderate":[73],"amount":[74],"training":[76],"data.":[77],"The":[78],"best":[79],"designs":[80],"perform":[81],"on":[82],"par":[83],"or":[84],"even":[85],"better":[86],"than":[87],"state-of-the-art":[89],"reference-based":[90],"algorithm":[92],"across":[93],"variety":[95],"comprising":[98],"different":[99],"degradation":[100],"types.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}