{"id":"https://openalex.org/W4408356047","doi":"https://doi.org/10.1109/icassp49660.2025.10889259","title":"From Characters to Subwords: Modeling Unit Conversion for Low-resource Speech Recognition","display_name":"From Characters to Subwords: Modeling Unit Conversion for Low-resource Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356047","doi":"https://doi.org/10.1109/icassp49660.2025.10889259"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101969071","display_name":"Yizhi Wang","orcid":"https://orcid.org/0000-0002-4469-4441"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhi Wang","raw_affiliation_strings":["Zhejiang University,Colleage of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Colleage of Computer Science and Technology,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102996603","display_name":"Haofei Zhang","orcid":"https://orcid.org/0000-0003-3247-6356"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofei Zhang","raw_affiliation_strings":["Zhejiang University,Colleage of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Colleage of Computer Science and Technology,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062037349","display_name":"Hui\u2010Qiong Wang","orcid":"https://orcid.org/0000-0002-0495-3146"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiqiong Wang","raw_affiliation_strings":["Zhejiang University,Ningbo Innovation Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Ningbo Innovation Center,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318678","display_name":"Li Sun","orcid":"https://orcid.org/0000-0002-2957-4214"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Sun","raw_affiliation_strings":["Zhejiang University,Ningbo Innovation Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Ningbo Innovation Center,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Zhejiang University,Colleage of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Colleage of Computer Science and Technology,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9484999775886536,"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":0.9484999775886536,"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/speech-recognition","display_name":"Speech recognition","score":0.7233210802078247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6378238201141357},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5473412275314331},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.48328474164009094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4050416648387909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3460840582847595},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11315608024597168}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7233210802078247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378238201141357},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5473412275314331},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.48328474164009094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4050416648387909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3460840582847595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11315608024597168},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2033436836","https://openalex.org/W2766219058","https://openalex.org/W2895417874","https://openalex.org/W2936774411","https://openalex.org/W2962784628","https://openalex.org/W2972652106","https://openalex.org/W2972818416","https://openalex.org/W3009129170","https://openalex.org/W3016010032","https://openalex.org/W3094841848","https://openalex.org/W3095732712","https://openalex.org/W3097777922","https://openalex.org/W3155453618","https://openalex.org/W3161127957","https://openalex.org/W3170360470","https://openalex.org/W3197813307","https://openalex.org/W3197849864","https://openalex.org/W3209976096","https://openalex.org/W4206191520","https://openalex.org/W4225827662","https://openalex.org/W4293363567","https://openalex.org/W4297841641","https://openalex.org/W4313415426","https://openalex.org/W4318484710","https://openalex.org/W4321510785","https://openalex.org/W4372260018","https://openalex.org/W4385245566","https://openalex.org/W4385572536","https://openalex.org/W4385822833","https://openalex.org/W6771467084","https://openalex.org/W6779202336","https://openalex.org/W6839026989"],"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":{"Multilingual":[0],"automatic":[1,48],"speech":[2,93,97],"recognition":[3,49],"(ASR)":[4],"models":[5],"greatly":[6],"facilitate":[7],"recognizing":[8],"low-resource":[9,66],"languages":[10,128],"by":[11],"sharing":[12],"representations":[13],"across":[14],"similar":[15],"languages.":[16,101],"However,":[17],"the":[18,71,86,91,105,115],"commonly":[19],"adopted":[20],"modeling":[21,41,76,90],"units,":[22],"e.g.,":[23],"character-level":[24,80,106],"modeling,":[25],"lack":[26],"language-specific":[27],"information,":[28],"resulting":[29],"in":[30],"a":[31,64,79],"susceptible":[32],"word":[33,137],"prediction":[34,107],"to":[35,55],"phonemes":[36],"and":[37,94,124],"characters.":[38],"Recently,":[39],"subword-level":[40],"has":[42],"demonstrated":[43],"significant":[44],"effectiveness":[45],"for":[46,89,110],"monolingual":[47],"systems,":[50],"while":[51],"it":[52],"is":[53,83],"adverse":[54],"cross-lingual":[56],"feature":[57],"sharing.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,103],"propose":[63],"novel":[65],"ASR":[67,81],"method":[68,134],"that":[69,131],"leverages":[70],"advantages":[72],"of":[73,114],"two":[74],"different":[75],"units.":[77],"Specifically,":[78],"model":[82],"trained":[84],"on":[85,120],"multilingual":[87],"dataset":[88],"short-term":[92],"learning":[95,111],"general":[96],"knowledge":[98],"from":[99],"relevant":[100],"Afterwards,":[102],"convert":[104],"into":[108],"subwords":[109],"contextual":[112],"information":[113],"target":[116],"language.":[117],"Extensive":[118],"experiments":[119],"Uyghur":[121],"with":[122],"Kazakh":[123],"Kyrgyz":[125],"as":[126],"auxiliary":[127],"have":[129],"shown":[130],"our":[132],"proposed":[133],"significantly":[135],"reduces":[136],"error":[138],"rate":[139],"(WER).":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}