{"id":"https://openalex.org/W4416799059","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249176","title":"Fast and Speaker-Independent Utterance Selection for ASR-Free CALL Systems of Minority Languages","display_name":"Fast and Speaker-Independent Utterance Selection for ASR-Free CALL Systems of Minority Languages","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799059","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249176"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Takaki Koshikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaki Koshikawa","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University,Sendai,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University,Sendai,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109012739","display_name":"Takashi Nose","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University,Sendai,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17288056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"825","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5038999915122986,"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":0.5038999915122986,"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/T12031","display_name":"Speech and dialogue systems","score":0.36809998750686646,"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/T10028","display_name":"Topic Modeling","score":0.061400000005960464,"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/utterance","display_name":"Utterance","score":0.7997999787330627},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.656499981880188},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6280999779701233},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5315999984741211},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5231000185012817},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41370001435279846},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111000061035156},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7997999787330627},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.656499981880188},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49880000948905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4959999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45350000262260437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41370001435279846},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":23,"referenced_works":["https://openalex.org/W208467601","https://openalex.org/W1494198834","https://openalex.org/W1586213061","https://openalex.org/W2005522781","https://openalex.org/W2095932476","https://openalex.org/W2740079178","https://openalex.org/W2889418345","https://openalex.org/W2963242190","https://openalex.org/W3004305221","https://openalex.org/W3005578234","https://openalex.org/W3095410713","https://openalex.org/W3115198358","https://openalex.org/W3167517705","https://openalex.org/W3197485712","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4225650814","https://openalex.org/W4281492411","https://openalex.org/W4288874105","https://openalex.org/W4377834644","https://openalex.org/W4386514310","https://openalex.org/W4402672068"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"utterance":[3,90],"selection":[4,91],"in":[5,128],"a":[6,40],"spoken":[7,125],"dialogue":[8,126],"system":[9],"designed":[10],"for":[11,123],"CALL":[12],"systems":[13,127],"of":[14,58],"minority":[15,129],"languages,":[16],"where":[17],"no":[18],"ASR":[19],"or":[20],"TTS":[21],"modules":[22],"are":[23],"available.":[24],"To":[25,54],"enable":[26],"speaker-independent":[27],"and":[28,38,73,81,104],"efficient":[29,124],"matching,":[30,60],"we":[31,61],"employ":[32],"SelfSupervised":[33],"Learning":[34],"(SSL)":[35],"speech":[36],"representations":[37],"introduce":[39],"lightweight":[41],"method":[42],"called":[43],"Speech2Token":[44],"(S2T),":[45],"which":[46],"converts":[47],"feature":[48],"vectors":[49],"into":[50],"discrete":[51],"token":[52],"sequences.":[53],"reduce":[55],"the":[56,102,119],"cost":[57],"similarity":[59],"further":[62],"apply":[63],"three":[64],"compression":[65],"techniques:":[66],"Deduplication":[67,106],"(Dedup),":[68],"Optimum":[69],"Code":[70],"Summarization":[71],"(OCS),":[72],"Greedy":[74],"Sequential":[75],"Optimization":[76],"(GSO).":[77],"Experiments":[78],"on":[79],"Japanese":[80],"Kaqchikel":[82],"datasets":[83],"show":[84],"that":[85],"using":[86],"SSL":[87],"features":[88,103],"improves":[89],"accuracy":[92,109],"by":[93,114],"20":[94],"points":[95],"compared":[96],"to":[97],"conventional":[98],"features.":[99],"Furthermore,":[100],"tokenizing":[101],"applying":[105],"achieves":[107],"comparable":[108],"while":[110],"reducing":[111],"response":[112],"time":[113],"nearly":[115],"50":[116],"%,":[117],"demonstrating":[118],"method'":[120],"s":[121],"practicality":[122],"language":[130],"settings.":[131]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}