{"id":"https://openalex.org/W4415432875","doi":"https://doi.org/10.21437/interspeech.2025-2069","title":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","display_name":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432875","doi":"https://doi.org/10.21437/interspeech.2025-2069"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2069","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2069","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032433720","display_name":"Karl El Hajal","orcid":"https://orcid.org/0000-0003-3128-335X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karl El Hajal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042970143","display_name":"Enno Hermann","orcid":"https://orcid.org/0000-0001-9945-1140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enno Hermann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036064749","display_name":"Sevada Hovsepyan","orcid":"https://orcid.org/0000-0001-8640-4206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sevada Hovsepyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathew Magimai Doss","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9909,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91862397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2760","last_page":"2764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9715999960899353,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9715999960899353,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9672999978065491,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9099000096321106,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.5325999855995178},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4065000116825104},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28060001134872437},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.2401999980211258}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6039000153541565},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4706999957561493},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3280999958515167},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2401999980211258}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2069","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2069","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}