{"id":"https://openalex.org/W4415432754","doi":"https://doi.org/10.21437/interspeech.2025-2768","title":"Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech","display_name":"Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432754","doi":"https://doi.org/10.21437/interspeech.2025-2768"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2768","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.eur.nl/en/publications/29034a02-e22c-4e6e-8b81-f7d66431b737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115902599","display_name":"Dimme de Groot","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dimme de Groot","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071210435","display_name":"Tanvina Patel","orcid":"https://orcid.org/0000-0002-9544-0038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanvina Patel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094342871","display_name":"Devendra Kayande","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devendra Kayande","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053209750","display_name":"Zhengjun Yue","orcid":"https://orcid.org/0000-0002-1101-549X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengjun Yue","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5115902599"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37833926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2740","last_page":"2744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11358","display_name":"Dysphagia Assessment and Management","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8270000219345093},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6496000289916992},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.5720999836921692},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47620001435279846},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.34049999713897705},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3296999931335449}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8270000219345093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686999797821045},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6496000289916992},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4763999879360199},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.3140999972820282},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C3018392663","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Speech sound","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27880001068115234}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-2768","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.eur.nl:openaire/29034a02-e22c-4e6e-8b81-f7d66431b737","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/29034a02-e22c-4e6e-8b81-f7d66431b737","pdf_url":null,"source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"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":"de Groot, D, Patel, T, Kayande, D, Scharenborg, O & Yue, Z 2025, 'Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 2740-2744. https://doi.org/10.21437/Interspeech.2025-2768","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2508.17980","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.17980","pdf_url":"https://arxiv.org/pdf/2508.17980","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:pure.eur.nl:openaire/29034a02-e22c-4e6e-8b81-f7d66431b737","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/29034a02-e22c-4e6e-8b81-f7d66431b737","pdf_url":null,"source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"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":"de Groot, D, Patel, T, Kayande, D, Scharenborg, O & Yue, Z 2025, 'Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 2740-2744. https://doi.org/10.21437/Interspeech.2025-2768","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,7,31,42,49,61,74,80,86,90,97,110,126],"poses":[2],"significant":[3],"challenges":[4],"for":[5,29],"automatic":[6],"recognition":[8,62,132],"(ASR)":[9],"systems":[10],"due":[11],"to":[12,51,92,127],"its":[13,129],"high":[14],"variability":[15],"and":[16,71,79,95,98,105,108,115],"reduced":[17],"intelligibility.":[18],"In":[19],"this":[20],"work":[21],"we":[22],"explore":[23],"the":[24,37,45,66,100,106,113,124],"use":[25],"of":[26,47,53,68,82,112],"diffusion":[27],"models":[28],"dysarthric":[30,48,60,85,96,117],"enhancement,":[32],"which":[33,56],"is":[34],"based":[35],"on":[36,77,123,131],"hypothesis":[38],"that":[39,52],"using":[40,103],"diffusion-based":[41,70],"enhancement":[43,75,91],"moves":[44],"distribution":[46],"closer":[50],"typical":[54,94],"speech,":[55],"could":[57],"potentially":[58],"improve":[59],"performance.":[63,133],"We":[64,88,119],"assess":[65,128],"effect":[67],"two":[69,83],"one":[72],"signal-processing-based":[73],"algorithms":[76],"intelligibility":[78],"quality":[81,111],"English":[84],"corpora.":[87],"applied":[89],"both":[93],"evaluate":[99],"ASR":[101],"performance":[102],"Whisper-Turbo,":[104],"subjective":[107],"objective":[109],"original":[114],"enhanced":[116,125],"speech.":[118],"also":[120],"fine-tuned":[121],"Whisper-Turbo":[122],"impact":[130]},"counts_by_year":[],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-23T00:00:00"}
