{"id":"https://openalex.org/W4406858842","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848811","title":"Data Selection using Spoken Language Identification for Low-Resource and Zero-Resource Speech Recognition","display_name":"Data Selection using Spoken Language Identification for Low-Resource and Zero-Resource Speech Recognition","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858842","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848811"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2433/297184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100701917","display_name":"Jianan Chen","orcid":"https://orcid.org/0000-0002-4607-3227"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianan Chen","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061781358","display_name":"Kawahara Tatsuya","orcid":"https://orcid.org/0000-0002-8474-7077"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9544000029563904,"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":0.9544000029563904,"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/T10860","display_name":"Speech and Audio Processing","score":0.900600016117096,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7575327754020691},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6967213749885559},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6649268865585327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5697563290596008},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5515987277030945},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5293254256248474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5116896629333496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3497745394706726},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16259056329727173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575327754020691},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6967213749885559},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6649268865585327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5697563290596008},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5515987277030945},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5293254256248474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5116896629333496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3497745394706726},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16259056329727173},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0006959862","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/297184","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"conference paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729899","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931497","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01221:0006959862","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/297184","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2038909419","https://openalex.org/W2184170932","https://openalex.org/W2395465351","https://openalex.org/W2514191708","https://openalex.org/W2895645998","https://openalex.org/W2963626623","https://openalex.org/W3024869864","https://openalex.org/W3139878283","https://openalex.org/W3167533889","https://openalex.org/W3167873515","https://openalex.org/W3202370288","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4206662530","https://openalex.org/W4313568641","https://openalex.org/W4319862472","https://openalex.org/W4322714819","https://openalex.org/W4372271612","https://openalex.org/W4385822875","https://openalex.org/W4391021440","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6787141514","https://openalex.org/W6806243479","https://openalex.org/W6857454988"],"related_works":["https://openalex.org/W3013650182","https://openalex.org/W2989283631","https://openalex.org/W4249605382","https://openalex.org/W4205762803","https://openalex.org/W4313491656","https://openalex.org/W3279617","https://openalex.org/W4402958497","https://openalex.org/W2898732673","https://openalex.org/W2535856026","https://openalex.org/W1991183963"],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1],"models":[2,55],"have":[3],"become":[4],"common":[5],"for":[6],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR)":[10],"tasks.":[11,28],"They":[12],"utilize":[13],"large-scale,":[14],"multilingual":[15],"datasets":[16],"to":[17,35,56,75,79],"learn":[18],"acoustic":[19],"features":[20],"and":[21,37,92,103],"then":[22],"are":[23],"finetuned":[24],"on":[25,90,100],"downstream":[26],"ASR":[27,87,98,124],"However,":[29],"their":[30],"performance":[31,89],"degrades":[32],"when":[33],"applied":[34],"low-resource":[36,77,91],"zero-resource":[38,94],"languages":[39,78],"lacking":[40],"data.":[41],"This":[42],"paper":[43],"introduces":[44],"a":[45,71],"new":[46],"data":[47,61,109],"selection":[48],"method":[49,121],"with":[50,81,105,126],"Spoken":[51],"Language":[52],"Identification":[53],"(SLI)":[54],"bring":[57],"non-target":[58,107],"language":[59,129],"speech":[60],"into":[62],"training.":[63],"With":[64],"the":[65,86,111,119],"help":[66],"of":[67],"phonetic":[68],"labels":[69],"as":[70],"universal":[72],"intermediate":[73],"representation":[74],"link":[76],"those":[80],"rich":[82],"resources,":[83],"we":[84],"enhance":[85],"system's":[88],"even":[93],"languages.":[95],"We":[96],"conducted":[97],"experiments":[99],"Marathi,":[101],"Assamese,":[102],"Panjabi":[104],"augmented":[106],"Hindi":[108],"in":[110],"CommonVoice":[112],"corpora.":[113],"The":[114],"experimental":[115],"results":[116],"show":[117],"that":[118],"proposed":[120],"can":[122],"train":[123],"systems":[125],"little":[127],"target":[128],"resource.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}