{"id":"https://openalex.org/W4402111244","doi":"https://doi.org/10.21437/interspeech.2024-1790","title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","display_name":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111244","doi":"https://doi.org/10.21437/interspeech.2024-1790"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1790","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.05554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100782321","display_name":"Jinpeng Li","orcid":"https://orcid.org/0000-0002-0633-6184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinpeng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100529121","display_name":"Yu Pu","orcid":"https://orcid.org/0009-0005-6428-1379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Pu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549873","display_name":"Qi Sun","orcid":"https://orcid.org/0009-0001-9135-8408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2514","last_page":"2518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12151","display_name":"Interpreting and Communication in Healthcare","score":0.8167999982833862,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12151","display_name":"Interpreting and Communication in Healthcare","score":0.8167999982833862,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.7026000022888184,"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":0.8357890844345093},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.8307284116744995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5935064554214478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5616261959075928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44094714522361755},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19937193393707275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357890844345093},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.8307284116744995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5935064554214478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5616261959075928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44094714522361755},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19937193393707275},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-1790","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.05554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.05554","pdf_url":"https://arxiv.org/pdf/2408.05554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.05554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.05554","pdf_url":"https://arxiv.org/pdf/2408.05554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1014351457","display_name":null,"funder_award_id":"62276153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111244.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2363093443","https://openalex.org/W4206915444","https://openalex.org/W4388766676","https://openalex.org/W2353302181","https://openalex.org/W2362181825","https://openalex.org/W2320680668","https://openalex.org/W2519027122","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Whisper":[0,41,64],"and":[1,54,57,75,104,129],"other":[2,140],"large-scale":[3],"automatic":[4],"speech":[5,53,83,102],"recognition":[6],"models":[7],"have":[8],"made":[9],"significant":[10],"progress":[11],"in":[12,126],"performance.":[13,116],"However,":[14],"their":[15],"performance":[16,39,81],"on":[17,42,65],"many":[18],"low-resource":[19],"languages,":[20],"such":[21],"as":[22,94],"Kazakh,":[23],"is":[24,28],"not":[25],"satisfactory.":[26],"It":[27],"worth":[29],"researching":[30],"how":[31],"to":[32,36,78,97,108,112,136,139],"utilize":[33],"low-cost":[34],"data":[35,56,103,107],"improve":[37,79,114],"the":[38,59,80,88,110,130,134],"of":[40,70,82],"under-represented":[43,141],"languages.":[44,142],"In":[45],"this":[46],"study,":[47],"we":[48,86,118],"utilized":[49],"easily":[50],"accessible":[51],"unpaired":[52],"text":[55],"combined":[58],"language":[60],"model":[61,111],"GPT":[62],"with":[63],"Kazakh.":[66],"We":[67],"implemented":[68],"end":[69],"transcript":[71],"(EOT)":[72],"judgment":[73],"modification":[74],"hallucination":[76],"penalty":[77],"recognition.":[84],"Further,":[85],"employed":[87],"decoding":[89],"average":[90],"token":[91],"log":[92],"probability":[93],"a":[95],"criterion":[96],"select":[98],"samples":[99],"from":[100],"unlabeled":[101],"used":[105],"pseudo-labeled":[106],"fine-tune":[109],"further":[113],"its":[115],"Ultimately,":[117],"achieved":[119],"more":[120],"than":[121],"10\\%":[122],"absolute":[123],"WER":[124],"reduction":[125],"multiple":[127],"experiments,":[128],"whole":[131],"process":[132],"has":[133],"potential":[135],"be":[137],"generalized":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}