{"id":"https://openalex.org/W2210138121","doi":null,"title":"Pronunciation Lexicon Development for Under-Resourced Languages Using Automatically Derived Subword Units: A Case Study on Scottish Gaelic","display_name":"Pronunciation Lexicon Development for Under-Resourced Languages Using Automatically Derived Subword Units: A Case Study on Scottish Gaelic","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2210138121","mag":"2210138121"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.epfl.ch:213710","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/213710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"parent_works":[],"lineage":["https://openalex.org/W2210138121"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/213710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044443491","display_name":"Marzieh Razavi","orcid":"https://orcid.org/0000-0001-6332-9661","observed_orcids":["https://orcid.org/0000-0001-6332-9661"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marzieh Razavi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6332-9661","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015798689","display_name":"Ramya Rasipuram","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramya Rasipuram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409","observed_orcids":["https://orcid.org/0000-0002-8714-1409"]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["IDIAP RESEARCH INSTITUTE"],"raw_orcid":"https://orcid.org/0000-0002-8714-1409","affiliations":[{"raw_affiliation_string":"IDIAP RESEARCH INSTITUTE","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6675,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70562247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0003000000142492354,"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/pronunciation-dictionary","display_name":"pronunciation dictionary","score":0.925000011920929},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8500000238418579},{"id":"https://openalex.org/keywords/scottish-gaelic","display_name":"Scottish Gaelic","score":0.8989999890327454},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.7009999752044678},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.8650000095367432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7480000257492065}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8932487964630127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973306775093079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5918999314308167},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5626412034034729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368870496749878},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.506208598613739},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45869535207748413},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:infoscience.epfl.ch:213710","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/213710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:213710","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/213710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/213710","raw_type":"Text"},{"id":"mag:2210138121","doi":null,"is_oa":false,"landing_page_url":"http://www.ilc.cnr.it/lrl2015/LRL2015_Presentation-11.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:213710","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/213710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2210138121.pdf","grobid_xml":"https://content.openalex.org/works/W2210138121.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W943204654","https://openalex.org/W1526516369","https://openalex.org/W1534441687","https://openalex.org/W2045211645","https://openalex.org/W2051530898","https://openalex.org/W2065927558","https://openalex.org/W2098624096","https://openalex.org/W2099415988","https://openalex.org/W2100768664","https://openalex.org/W2152671307","https://openalex.org/W2170353620","https://openalex.org/W2401464865"],"related_works":["https://openalex.org/W2614744999","https://openalex.org/W1548357021","https://openalex.org/W2917786826","https://openalex.org/W3042354609","https://openalex.org/W6989346467","https://openalex.org/W7099847917","https://openalex.org/W7066146595","https://openalex.org/W2051530898","https://openalex.org/W2152671307","https://openalex.org/W1483055307"],"abstract_inverted_index":{"Developing":[0],"a":[1,5,54,71,93,135],"phonetic":[2,123],"lexicon":[3,68,94],"for":[4,21,27,61,137],"language":[6,157],"requires":[7],"linguistic":[8,29,142,152],"knowledge":[9,121,143,153],"as":[10,12],"well":[11],"human":[13],"effort,":[14],"which":[15],"may":[16],"not":[17,87],"be":[18,34,89,107],"available,":[19],"particularly":[20],"under-resourced":[22,73,156],"languages.To":[23],"avoid":[24],"the":[25,28,39,43,47,51,84,111,114,119,132,148,155],"need":[26],"knowledge,":[30],"acoustic":[31,140,150],"information":[32],"can":[33,86,105],"used":[35],"to":[36,109,160],"automatically":[37],"obtain":[38],"subword":[40,65,116,164],"units":[41,66,117,124],"and":[42,67,74,118,141,151],"associated":[44],"pronunciations.Towards":[45],"that,":[46],"present":[48],"paper":[49],"investigates":[50],"potential":[52],"of":[53,64,154],"recently":[55],"proposed":[56],"hidden":[57],"Markov":[58],"model":[59],"formalism":[60,85,133],"automatic":[62,100,163],"derivation":[63],"development":[69],"on":[70],"truly":[72],"endangered":[75],"language,":[76],"more":[77,128],"precisely":[78,129],"Scottish":[79],"Gaelic.Our":[80],"studies":[81],"show":[82],"that":[83,95],"only":[88],"useful":[90],"in":[91,97,158],"developing":[92],"helps":[96],"building":[98],"better":[99],"speech":[101],"recognition":[102],"systems,":[103],"but":[104],"also":[106],"extended":[108],"find":[110],"relationship":[112],"between":[113],"derived":[115],"existing":[120],"about":[122],"from":[125,144],"resource-rich":[126],"languages,":[127],"multilingual":[130],"phones.Thus,":[131],"paves":[134],"path":[136],"systematically":[138],"combining":[139],"multiple":[145],"languages":[146],"with":[147],"limited":[149],"order":[159],"develop":[161],"phone-like":[162],"unit":[165],"based":[166],"lexical":[167],"resources.":[168]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}