{"id":"https://openalex.org/W4385823463","doi":"https://doi.org/10.21437/interspeech.2023-222","title":"Dysarthric Speech Recognition, Detection and Classification using Raw Phase and Magnitude Spectra","display_name":"Dysarthric Speech Recognition, Detection and Classification using Raw Phase and Magnitude Spectra","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823463","doi":"https://doi.org/10.21437/interspeech.2023-222"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-222","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_543cf325-9481-4534-9c57-f1da21cfbd7f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053209750","display_name":"Zhengjun Yue","orcid":"https://orcid.org/0000-0002-1101-549X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]},{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB","NL"],"is_corresponding":true,"raw_author_name":"Zhengjun Yue","raw_affiliation_strings":["Department of Engineering, King's College London, UK","Multimedia Computing Group, Delft University of Technology, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["Department of Engineering, King's College London, UK","Speech Group, Machine Intelligence Laboratory, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Speech Group, Machine Intelligence Laboratory, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["Department of Engineering, King's College London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, UK","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053209750"],"corresponding_institution_ids":["https://openalex.org/I183935753","https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":1.0662,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81607871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1533","last_page":"1537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9478999972343445,"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":0.9478999972343445,"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":0.9460999965667725,"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/magnitude","display_name":"Magnitude (astronomy)","score":0.6579619646072388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6360663771629333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5849020481109619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43684515357017517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.373919814825058},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1936037838459015}],"concepts":[{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.6579619646072388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6360663771629333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849020481109619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43684515357017517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.373919814825058},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1936037838459015},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-222","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:3dd58d3b-4b5a-4eca-aedd-72bc523a2979","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:3dd58d3b-4b5a-4eca-aedd-72bc523a2979","pdf_url":"https://repository.tudelft.nl/file/File_543cf325-9481-4534-9c57-f1da21cfbd7f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"pmh:oai:repository@napier.ac.uk:3585808","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585808","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"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":"Presentation / Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:3dd58d3b-4b5a-4eca-aedd-72bc523a2979","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:3dd58d3b-4b5a-4eca-aedd-72bc523a2979","pdf_url":"https://repository.tudelft.nl/file/File_543cf325-9481-4534-9c57-f1da21cfbd7f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G3297227137","display_name":null,"funder_award_id":"EP/R012180/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823463.pdf","grobid_xml":"https://content.openalex.org/works/W4385823463.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1524333225","https://openalex.org/W1528620860","https://openalex.org/W1550888325","https://openalex.org/W2018363392","https://openalex.org/W2052043304","https://openalex.org/W2101234009","https://openalex.org/W2116217121","https://openalex.org/W2124460610","https://openalex.org/W2131548063","https://openalex.org/W2138731530","https://openalex.org/W2168709618","https://openalex.org/W2170787898","https://openalex.org/W2400436994","https://openalex.org/W2794209590","https://openalex.org/W2899771611","https://openalex.org/W2913682984","https://openalex.org/W2964227577","https://openalex.org/W2973053574","https://openalex.org/W2996636445","https://openalex.org/W3013783381","https://openalex.org/W3099550332","https://openalex.org/W3134043075","https://openalex.org/W3163845842","https://openalex.org/W3174329270","https://openalex.org/W3197553328","https://openalex.org/W3204675901","https://openalex.org/W4224315877","https://openalex.org/W4224918597","https://openalex.org/W4224932111","https://openalex.org/W4232318280","https://openalex.org/W4293354476","https://openalex.org/W4296068432","https://openalex.org/W4297030419","https://openalex.org/W4304109176","https://openalex.org/W4304109208","https://openalex.org/W4306169256","https://openalex.org/W4313305398","https://openalex.org/W4319998061"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2163831990","https://openalex.org/W2368779261","https://openalex.org/W3003836766","https://openalex.org/W2046077695","https://openalex.org/W2378160586","https://openalex.org/W2042327336","https://openalex.org/W2996038082","https://openalex.org/W3047965787"],"abstract_inverted_index":{"<p>In":[0],"this":[1],"paper,":[2],"we":[3,24,65],"explore":[4],"the":[5,9,26,38,80,83,91,102,105],"effectiveness":[6],"of":[7,28,52,55,82,122],"deploying":[8],"raw":[10,30,39,84],"phase":[11,85],"and":[12,20,42,48,58,69,86,93,98,107,112,124,128,133],"magnitude":[13,40,87],"spectra":[14],"for":[15,61,113,126],"dysarthric":[16,109,127],"speech":[17,110,130],"recognition,":[18],"detection":[19,92],"classification.":[21],"In":[22,78],"particular,":[23],"scrutinise":[25],"usefulness":[27],"various":[29,67],"phase-based":[31],"representations":[32],"along":[33],"with":[34,37],"their":[35,75],"combinations":[36],"spectrum":[41],"filterbank":[43],"features.":[44],"We":[45,100],"employed":[46],"single":[47],"multi-stream":[49],"architectures":[50],"consisting":[51],"a":[53],"cascade":[54],"convolutional,":[56],"recurrent":[57],"fully-connected":[59],"layers":[60],"acoustic":[62],"modelling.":[63],"Furthermore,":[64],"investigate":[66],"configurations":[68],"fusion":[70],"schemes":[71],"as":[72,74],"well":[73],"training":[76],"dynamics.":[77],"addition,":[79],"accuracies":[81],"based":[88],"systems":[89],"in":[90],"classification":[94],"tasks":[95],"are":[96],"studied":[97],"discussed.":[99],"report":[101],"performance":[103],"on":[104,131,135],"UASpeech":[106],"TORGO":[108,132],"databases":[111],"different":[114],"severity":[115],"levels.":[116],"Our":[117],"best":[118],"system":[119],"achieved":[120],"WERs":[121],"31.2%":[123],"9.1%":[125],"typical":[129],"30.2%":[134],"UASpeech,":[136],"respectively.</p>":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}