{"id":"https://openalex.org/W7148506074","doi":"https://doi.org/10.1109/asru65441.2025.11434685","title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","display_name":"Benchmarking Prosody Encoding in Discrete Speech Tokens","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148506074","doi":"https://doi.org/10.1109/asru65441.2025.11434685"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5113361539","display_name":"Kentaro Onda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kentaro Onda","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098968","display_name":"Satoru Fukayama","orcid":"https://orcid.org/0000-0001-6506-2796"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Fukayama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010715755","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3012-1607"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132820863","display_name":"Nobuaki Minematsu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113361539"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8757358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5532000064849854,"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":0.5532000064849854,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.16110000014305115,"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/T12031","display_name":"Speech and dialogue systems","score":0.14869999885559082,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6442000269889832},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.47699999809265137},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4088999927043915},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2957000136375427},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.27889999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931999921798706},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6442000269889832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5541999936103821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4894999861717224},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46959999203681946},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2140686411","https://openalex.org/W2471520273","https://openalex.org/W3099284785","https://openalex.org/W3127686677","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210177631","https://openalex.org/W3215615641","https://openalex.org/W4281492411","https://openalex.org/W4307680525","https://openalex.org/W4375868953","https://openalex.org/W4381786045","https://openalex.org/W4385822336","https://openalex.org/W4385822488","https://openalex.org/W4385822683","https://openalex.org/W4389524500","https://openalex.org/W4392903159","https://openalex.org/W4392904157","https://openalex.org/W4392909068","https://openalex.org/W4392909760","https://openalex.org/W4402111497","https://openalex.org/W4402111612","https://openalex.org/W4402111789","https://openalex.org/W4406461437","https://openalex.org/W4406461625","https://openalex.org/W4408352488","https://openalex.org/W4410770311","https://openalex.org/W4415433821","https://openalex.org/W4415433890","https://openalex.org/W4415433896"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"discrete":[1,32,104,140],"tokens":[2,33,105],"derived":[3],"from":[4,40],"self-supervised":[5],"learning":[6],"(SSL)":[7],"models":[8,21,45,75],"via":[9],"k-means":[10],"clustering":[11],"have":[12],"been":[13,97],"actively":[14],"studied":[15],"as":[16,23,57],"pseudo-text":[17],"in":[18,37],"speech":[19,73],"language":[20,44,74],"and":[22,80],"efficient":[24],"intermediate":[25],"representations":[26],"for":[27,138],"various":[28],"tasks.":[29,48],"However,":[30],"these":[31],"are":[34,76],"typically":[35],"learned":[36],"advance,":[38],"separately":[39],"the":[41,58,63,87,101,129],"training":[42],"of":[43,65,103],"or":[46,62],"downstream":[47],"As":[49],"a":[50,117],"result,":[51],"choices":[52],"related":[53],"to":[54,78,106,128,134],"discretization,":[55],"such":[56],"SSL":[59],"model":[60],"used":[61],"number":[64],"clusters,":[66],"must":[67],"be":[68],"made":[69],"heuristically.":[70],"In":[71],"particular,":[72],"expected":[77],"understand":[79],"generate":[81],"responses":[82],"that":[83],"reflect":[84],"not":[85],"only":[86],"semantic":[88],"content":[89],"but":[90],"also":[91],"prosodic":[92,108,122],"features.":[93],"Yet,":[94],"there":[95],"has":[96],"limited":[98],"research":[99],"on":[100,121,125],"ability":[102],"capture":[107],"information.":[109],"To":[110],"address":[111],"this":[112,114],"gap,":[113],"study":[115],"conducts":[116],"comprehensive":[118],"analysis":[119],"focusing":[120],"encoding":[123],"based":[124],"their":[126],"sensitivity":[127],"artificially":[130],"modified":[131],"prosody,":[132],"aiming":[133],"provide":[135],"practical":[136],"guidelines":[137],"designing":[139],"tokens.":[141]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}