{"id":"https://openalex.org/W4405794758","doi":"https://doi.org/10.1145/3700410.3702114","title":"Reference-free automatic speech severity evaluation using acoustic unit language modelling","display_name":"Reference-free automatic speech severity evaluation using acoustic unit language modelling","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4405794758","doi":"https://doi.org/10.1145/3700410.3702114"},"language":"en","primary_location":{"id":"doi:10.1145/3700410.3702114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3700410.3702114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.00639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019343311","display_name":"Bence Mark Halpern","orcid":"https://orcid.org/0000-0001-8787-359X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bence Mark Halpern","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8787-359X","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9993000030517578,"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":0.754503607749939},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5679585933685303},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.47582533955574036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4509444236755371},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4472985565662384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33615273237228394},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0685499906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754503607749939},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5679585933685303},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.47582533955574036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4509444236755371},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4472985565662384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33615273237228394},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0685499906539917},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3700410.3702114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3700410.3702114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.00639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.00639","pdf_url":"https://arxiv.org/pdf/2510.00639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.00639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.00639","pdf_url":"https://arxiv.org/pdf/2510.00639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405794758.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W115710901","https://openalex.org/W1574170747","https://openalex.org/W1963718576","https://openalex.org/W2022939667","https://openalex.org/W2031072412","https://openalex.org/W2068449915","https://openalex.org/W2069335787","https://openalex.org/W2077708378","https://openalex.org/W2084627109","https://openalex.org/W2107570013","https://openalex.org/W2149768999","https://openalex.org/W2186025153","https://openalex.org/W2403339321","https://openalex.org/W2578167459","https://openalex.org/W2742150759","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W3009445194","https://openalex.org/W3030437843","https://openalex.org/W3195423934","https://openalex.org/W3207399576","https://openalex.org/W3209984917","https://openalex.org/W3211022491","https://openalex.org/W4200300291","https://openalex.org/W4296068974","https://openalex.org/W4310415633","https://openalex.org/W4360938237","https://openalex.org/W4372260311","https://openalex.org/W4372260534","https://openalex.org/W4391021405","https://openalex.org/W4391021560"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W2371343292","https://openalex.org/W629290331","https://openalex.org/W617685022","https://openalex.org/W1509983653","https://openalex.org/W3215563689","https://openalex.org/W610590827","https://openalex.org/W591599671","https://openalex.org/W1556748146","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Speech":[0],"severity":[1,17,67,105],"evaluation":[2,62,68],"is":[3,151],"becoming":[4],"increasingly":[5],"important":[6],"as":[7,51],"the":[8,89,94,119,130,143],"economic":[9],"burden":[10],"of":[11,31,132],"speech":[12,16,32,39,53,60,84,104],"disorders":[13],"grows.":[14],"Current":[15],"models":[18,36,136],"often":[19],"struggle":[20],"with":[21,66],"generalization,":[22],"learning":[23],"dataset-specific":[24],"acoustic":[25,114],"cues":[26],"rather":[27],"than":[28],"meaningful":[29],"correlates":[30],"severity.":[33],"Furthermore,":[34],"many":[35],"require":[37],"reference":[38],"or":[40],"a":[41,74,99],"transcript,":[42],"limiting":[43],"their":[44],"applicability":[45],"in":[46,142],"ecologically":[47],"valid":[48],"scenarios,":[49],"such":[50],"spontaneous":[52],"evaluation.":[54,106],"Previous":[55],"research":[56],"indicated":[57],"that":[58,149],"automatic":[59],"naturalness":[61],"scores":[63],"correlate":[64],"strongly":[65],"scores,":[69],"leading":[70],"us":[71],"to":[72,97,153,160],"explore":[73],"reference-free":[75,123],"method,":[76],"SpeechLMScore,":[77],"which":[78],"does":[79],"not":[80],"rely":[81],"on":[82,93,134],"pathological":[83],"data.":[85],"Additionally,":[86],"we":[87,128],"present":[88],"NKI-SpeechRT":[90,144],"dataset,":[91,96],"based":[92],"NKI-CCRT":[95],"provide":[98],"more":[100],"comprehensive":[101],"foundation":[102],"for":[103],"This":[107],"study":[108],"evaluates":[109],"whether":[110],"SpeechLMScore":[111,150],"outperforms":[112],"traditional":[113,161],"feature-based":[115],"approaches":[116],"and":[117,124,155],"assesses":[118],"performance":[120,158],"gap":[121],"between":[122],"reference-based":[125],"models.":[126],"Moreover,":[127],"examine":[129],"impact":[131],"noise":[133,140,154],"these":[135],"by":[137],"utilizing":[138],"subjective":[139],"ratings":[141],"dataset.":[145],"The":[146],"results":[147],"demonstrate":[148],"robust":[152],"offers":[156],"superior":[157],"compared":[159],"approaches.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}