{"id":"https://openalex.org/W4405710095","doi":"https://doi.org/10.1109/iscslp63861.2024.10800186","title":"Low-Resourced Speech Recognition for Iu Mien Language via Weakly-Supervised Phoneme-Based Multilingual Pretraining","display_name":"Low-Resourced Speech Recognition for Iu Mien Language via Weakly-Supervised Phoneme-Based Multilingual Pretraining","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405710095","doi":"https://doi.org/10.1109/iscslp63861.2024.10800186"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"Lukuan Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lukuan Dong","raw_affiliation_strings":["School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061782682","display_name":"Donghong Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghong Qin","raw_affiliation_strings":["School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fengbo Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengbo Bai","raw_affiliation_strings":["School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fanhua Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanhua Song","raw_affiliation_strings":["School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663508","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0002-1128-0752"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711699","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-5041-0532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Xu","raw_affiliation_strings":["School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangxi Minzu University,AI and Big Data International Cooperation Joint Laboratory,Nanning","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21327102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.925599992275238,"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":0.925599992275238,"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/computer-science","display_name":"Computer science","score":0.7581369280815125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6757000088691711},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4597158432006836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39557918906211853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581369280815125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6757000088691711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4597158432006836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39557918906211853}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":16,"referenced_works":["https://openalex.org/W1895481600","https://openalex.org/W2127141656","https://openalex.org/W2545177271","https://openalex.org/W2896457183","https://openalex.org/W2939297570","https://openalex.org/W2963250244","https://openalex.org/W3096396467","https://openalex.org/W3096673492","https://openalex.org/W3213029956","https://openalex.org/W4285172509","https://openalex.org/W6679855610","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6798761973","https://openalex.org/W6847363464","https://openalex.org/W6869458412"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,36],"mainstream":[1],"automatic":[2],"speech":[3,16,61,86],"recognition":[4],"(ASR)":[5],"technology":[6],"usually":[7],"requires":[8],"hundreds":[9],"to":[10,20,111,129],"thousands":[11],"of":[12,14,45,70],"hours":[13,69],"annotated":[15,60],"data.":[17,35],"Three":[18],"approaches":[19,82,114],"low-resourced":[21,54,116],"ASR":[22],"are":[23,90],"phoneme":[24,122],"or":[25],"subword":[26,130],"based":[27,91],"supervised":[28],"pretraining,":[29,149],"and":[30,52,78,132],"self-supervised":[31],"pretraining":[32],"over":[33,100],"multilingual":[34,148],"Iu":[37,72,84],"Mien":[38,73,85],"language":[39,44],"is":[40,53,62,119],"the":[41,46,56,59,80,93,101,105,112,139,145,151],"main":[42],"ethnic":[43,48],"Yao":[47],"group":[49],"in":[50,55],"China":[51],"sense":[57],"that":[58,121],"very":[63],"limited.":[64],"With":[65],"less":[66],"than":[67],"10":[68,102],"transcribed":[71],"language,":[74],"this":[75],"paper":[76],"investigates":[77],"compares":[79],"three":[81,96,113],"for":[83,115],"recognition.":[87],"Our":[88],"experiments":[89],"on":[92],"recently":[94],"released,":[95],"backbone":[97],"models":[98],"pretrained":[99],"languages":[103],"from":[104],"CommonVoice":[106],"dataset":[107],"(CV-Lang10),":[108],"which":[109],"correspond":[110],"ASR.":[117],"It":[118],"found":[120],"supervision":[123,131],"can":[124],"achieve":[125],"better":[126],"results":[127],"compared":[128],"self-supervision,":[133],"thereby":[134],"providing":[135],"higher":[136],"data-efficiency.":[137],"Particularly,":[138],"Whistle":[140],"models,":[141],"i.e.,":[142],"obtained":[143],"by":[144],"weakly-supervised":[146],"phoneme-based":[147],"obtain":[150],"most":[152],"competitive":[153],"results.":[154]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}