{"id":"https://openalex.org/W3142135748","doi":"https://doi.org/10.21437/interspeech.2021-1434","title":"Phoneme Recognition Through Fine Tuning of Phonetic Representations: A Case Study on Luhya Language Varieties","display_name":"Phoneme Recognition Through Fine Tuning of Phonetic Representations: A Case Study on Luhya Language Varieties","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3142135748","doi":"https://doi.org/10.21437/interspeech.2021-1434","mag":"3142135748"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.01624","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048239088","display_name":"Kathleen Siminyu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen Siminyu","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinjian Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["George Mason University, Fairfax, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, United States","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070180583","display_name":"Michael R. Marlo","orcid":"https://orcid.org/0000-0002-9944-9726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael R. Marlo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.7869060039520264},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6979101896286011},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6494097113609314},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5533836483955383},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5402277708053589},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5394106507301331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5070509910583496},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.47499147057533264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4746582806110382},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45122426748275757},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4383695721626282},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43551063537597656},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27859726548194885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869060039520264},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6979101896286011},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6494097113609314},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5533836483955383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5402277708053589},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5394106507301331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5070509910583496},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.47499147057533264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4746582806110382},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45122426748275757},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4383695721626282},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43551063537597656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27859726548194885},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.01624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01624","pdf_url":"https://arxiv.org/pdf/2104.01624","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3142135748","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.01624.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.01624","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.01624","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01624","pdf_url":"https://arxiv.org/pdf/2104.01624","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3142135748.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W425337973","https://openalex.org/W581390210","https://openalex.org/W2060277733","https://openalex.org/W2127141656","https://openalex.org/W2784121710","https://openalex.org/W2805993470","https://openalex.org/W2887920589","https://openalex.org/W2963026768","https://openalex.org/W2964172053","https://openalex.org/W2966841179","https://openalex.org/W2970848427","https://openalex.org/W3006988520","https://openalex.org/W3015585292","https://openalex.org/W3015877095","https://openalex.org/W3035485128","https://openalex.org/W3036601975","https://openalex.org/W3099782249"],"related_works":["https://openalex.org/W3197687261","https://openalex.org/W3008675085","https://openalex.org/W2167771929","https://openalex.org/W144374866","https://openalex.org/W3184789469","https://openalex.org/W3029693316","https://openalex.org/W2286601967","https://openalex.org/W2115605521","https://openalex.org/W2045072997","https://openalex.org/W2132822495","https://openalex.org/W2955724459","https://openalex.org/W2058489985","https://openalex.org/W2964309797","https://openalex.org/W3177967534","https://openalex.org/W2108582047","https://openalex.org/W3105242324","https://openalex.org/W244415383","https://openalex.org/W2903409363","https://openalex.org/W3095706145","https://openalex.org/W2963790883"],"abstract_inverted_index":{"Models":[0],"pre-trained":[1],"on":[2,22,33,104],"multiple":[3],"languages":[4],"have":[5],"shown":[6],"significant":[7,153],"promise":[8],"for":[9,14,29,71],"improving":[10],"speech":[11],"recognition,":[12],"particularly":[13],"low-resource":[15],"languages.":[16],"In":[17],"this":[18],"work,":[19],"we":[20,66],"focus":[21],"phoneme":[23],"recognition":[24,31,69,128],"using":[25,131],"Allosaurus,":[26,145],"a":[27,41,47,62,114],"method":[28],"multilingual":[30],"based":[32],"phonetic":[34],"annotation,":[35],"which":[36],"incorporates":[37],"phonological":[38],"knowledge":[39],"through":[40],"language-dependent":[42],"allophone":[43],"layer":[44],"that":[45,54,142],"associates":[46],"universal":[48],"narrow":[49],"phone-set":[50],"with":[51,147],"the":[52,78,94,105],"phonemes":[53],"appear":[55],"in":[56,61,120,155],"each":[57],"language.":[58],"To":[59,88],"evaluate":[60],"challenging":[63],"real-world":[64],"scenario,":[65],"curate":[67],"phone":[68,156],"datasets":[70,92,132],"Bukusu":[72],"and":[73,85,126],"Saamia,":[74],"two":[75],"varieties":[76],"of":[77,82,96,107,133,144],"Luhya":[79],"language":[80,116],"cluster":[81],"western":[83],"Kenya":[84],"eastern":[86],"Uganda.":[87],"our":[89],"knowledge,":[90],"these":[91],"are":[93],"first":[95],"their":[97],"kind.":[98],"We":[99,122,140],"carry":[100],"out":[101],"similar":[102],"experiments":[103],"dataset":[106],"an":[108],"endangered":[109],"Tangkhulic":[110],"language,":[111],"East":[112],"Tusom,":[113],"Tibeto-Burman":[115],"variety":[117],"spoken":[118],"mostly":[119],"India.":[121],"explore":[123],"both":[124],"zero-shot":[125],"few-shot":[127],"by":[129],"fine-tuning":[130,143],"varying":[134],"sizes":[135],"(10":[136],"to":[137,152],"1000":[138],"utterances).":[139],"find":[141],"even":[146],"just":[148],"100":[149],"utterances,":[150],"leads":[151],"improvements":[154],"error":[157],"rates.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
