{"id":"https://openalex.org/W4297841554","doi":"https://doi.org/10.21437/interspeech.2022-838","title":"Cross-dialect lexicon optimisation for an endangered language ASR system: the case of Irish","display_name":"Cross-dialect lexicon optimisation for an endangered language ASR system: the case of Irish","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841554","doi":"https://doi.org/10.21437/interspeech.2022-838"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-838","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-838","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17863/cam.93399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065119778","display_name":"Liam Lonergan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liam Lonergan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027476226","display_name":"Mengjie Qian","orcid":"https://orcid.org/0000-0003-2614-5411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengjie Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073423505","display_name":"Neasa N\u00ed Chiar\u00e1in","orcid":"https://orcid.org/0000-0002-4669-5667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neasa N\u00ed Chiar\u00e1in","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029071500","display_name":"Christer Gobl","orcid":"https://orcid.org/0000-0002-5958-3891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christer Gobl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001492005","display_name":"Ailbhe N\u0131\u0301 Chasaide","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ailbhe N\u00ed Chasaide","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":0.3362,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55188479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4865","last_page":"4869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T12031","display_name":"Speech and dialogue systems","score":0.9908999800682068,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9779999852180481,"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/lexicon","display_name":"Lexicon","score":0.8134908676147461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6771976351737976},{"id":"https://openalex.org/keywords/endangered-species","display_name":"Endangered species","score":0.6613243818283081},{"id":"https://openalex.org/keywords/irish","display_name":"Irish","score":0.6497702598571777},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5121586322784424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4598700702190399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3868473768234253},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12185847759246826},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06721508502960205}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8134908676147461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6771976351737976},{"id":"https://openalex.org/C179345059","wikidata":"https://www.wikidata.org/wiki/Q11394","display_name":"Endangered species","level":3,"score":0.6613243818283081},{"id":"https://openalex.org/C2780623531","wikidata":"https://www.wikidata.org/wiki/Q9142","display_name":"Irish","level":2,"score":0.6497702598571777},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5121586322784424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4598700702190399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3868473768234253},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12185847759246826},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06721508502960205},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-838","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-838","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/345977","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/345977","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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 Object"},{"id":"doi:10.17863/cam.93399","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.93399","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.17863/cam.93399","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.93399","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4230257923","https://openalex.org/W2487369564","https://openalex.org/W2041625401","https://openalex.org/W3187790117","https://openalex.org/W4234481033","https://openalex.org/W579276689","https://openalex.org/W2416760710","https://openalex.org/W2123137480","https://openalex.org/W1831473261","https://openalex.org/W4293870971"],"abstract_inverted_index":{"Lexicon":[0],"optimisation":[1],"strategies,":[2],"addressing":[3],"the":[4,42,74,111,118,154,160,179,184],"problem":[5],"of":[6,33,156],"dialect":[7,85,102],"divergence,":[8],"are":[9],"tested":[10,78,124],"in":[11,18,52,110],"an":[12],"ASR":[13,62],"system":[14,45,50,63],"for":[15,174],"Irish.":[16],"As":[17],"many":[19],"endangered":[20],"languages,":[21],"Irish":[22],"has":[23],"no":[24],"spoken":[25],"standard,":[26],"but":[27,168],"rather,":[28],"three":[29],"very":[30],"different":[31],"dialects":[32],"Ulster":[34],"(Ul),":[35],"Connaught":[36],"(Co)":[37],"and":[38,46,121,151,172],"Munster":[39],"(Mu).":[40],"Furthermore,":[41],"complex":[43],"sound":[44],"ancient,":[47],"opaque":[48],"writing":[49],"result":[51],"sound-to-grapheme":[53],"mappings":[54],"that":[55],"differ":[56],"considerably":[57],"across":[58,73],"dialects.":[59,75],"A":[60],"hybrid":[61],"was":[64],"trained":[65],"on":[66],"(predominantly)":[67],"native":[68],"speaker":[69],"speech":[70],"data,":[71],"balanced":[72],"Experiment":[76],"1":[77],"whether":[79,125],"a":[80,97,140,169],"Global":[81,114],"lexicon,":[82],"which":[83,177],"captures":[84],"variant":[86],"forms":[87],"with":[88],"relatively":[89,164],"abstract":[90],"representations,":[91],"can":[92],"perform":[93],"as":[94,96,159],"well":[95],"Multi-dialect":[98],"lexicon":[99,115],"containing":[100],"all":[101,149],"variants.":[103],"Three":[104],"dialect-specific":[105],"lexicons":[106],"were":[107],"also":[108],"included":[109,137],"tests.":[112],"The":[113],"did":[116],"yield":[117],"best":[119],"performance":[120],"experiment":[122],"2":[123],"further":[126,132],"reductions":[127],"to":[128,148,183],"its":[129,134],"phoneset":[130,185],"might":[131],"enhance":[133],"performance.":[135],"These":[136],"(i)":[138],"merging":[139,153],"Tense-Lax":[141],"contrast":[142,155],"among":[143],"coronal":[144],"sonorants,":[145,158],"not":[146],"common":[147],"dialects,":[150],"(ii)":[152],"voiceless-voiced":[157],"voiceless":[161],"member":[162],"is":[163,178],"infrequent.":[165],"Results":[166],"showed":[167],"slight":[170],"enhancement":[171],"only":[173],"Mu":[175],"dialect,":[176],"one":[180],"most":[181],"aligned":[182],"reduction.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}