{"id":"https://openalex.org/W2787760419","doi":null,"title":"Evaluating phonemic transcription of low-resource tonal languages for language documentation","display_name":"Evaluating phonemic transcription of low-resource tonal languages for language documentation","publication_year":2018,"publication_date":"2018-05-07","ids":{"openalex":"https://openalex.org/W2787760419","mag":"2787760419"},"language":"en","primary_location":{"id":"pmh:oai:HAL:halshs-01709648v4","doi":null,"is_oa":true,"landing_page_url":"https://shs.hal.science/halshs-01709648","pdf_url":"https://shs.hal.science/halshs-01709648v4/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://aclanthology.org/L18-1530","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://shs.hal.science/halshs-01709648v4/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010981457","display_name":"Oliver Adams","orcid":"https://orcid.org/0000-0002-5145-9589","observed_orcids":["https://orcid.org/0000-0002-5145-9589"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Oliver Adams","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":"https://orcid.org/0000-0002-5145-9589","affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673","observed_orcids":["https://orcid.org/0000-0003-4363-1673"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Trevor Cohn","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":"https://orcid.org/0000-0003-4363-1673","affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789","observed_orcids":["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"],"raw_orcid":"https://orcid.org/0000-0002-2072-3789","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000564128","display_name":"Hilaria Cruz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hilaria Cruz","raw_affiliation_strings":["Dartmouth Coll., Hanover#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth Coll., Hanover#TAB#","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026383657","display_name":"Steven Bird","orcid":"https://orcid.org/0000-0003-3782-7733","observed_orcids":["https://orcid.org/0000-0003-3782-7733"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I29894533","display_name":"Charles Darwin University","ror":"https://ror.org/048zcaj52","country_code":"AU","type":"education","lineage":["https://openalex.org/I29894533"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Steven Bird","raw_affiliation_strings":["Charles Darwin University","Lawrence Berkeley National Laboratory [Berkeley]"],"raw_orcid":"https://orcid.org/0000-0003-3782-7733","affiliations":[{"raw_affiliation_string":"Charles Darwin University","institution_ids":["https://openalex.org/I29894533"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory [Berkeley]","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086971174","display_name":"Alexis Michaud","orcid":"https://orcid.org/0000-0003-1165-2680","observed_orcids":["https://orcid.org/0000-0003-1165-2680"]},"institutions":[{"id":"https://openalex.org/I4387153690","display_name":"Langues et Civilisations \u00e0 Tradition Orale","ror":"https://ror.org/025esck76","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I162346809","https://openalex.org/I182627622","https://openalex.org/I4387153690"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexis Michaud","raw_affiliation_strings":["Langues et civilisations \u00e0 tradition orale"],"raw_orcid":"https://orcid.org/0000-0003-1165-2680","affiliations":[{"raw_affiliation_string":"Langues et civilisations \u00e0 tradition orale","institution_ids":["https://openalex.org/I4387153690"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7584,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93387896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3356","last_page":"3365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0017000000225380063,"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/T10860","display_name":"Speech and Audio Processing","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phonemic-transcription","display_name":"phonemic transcription","score":0.9409999847412109},{"id":"https://openalex.org/keywords/tone-languages","display_name":"tonal languages","score":0.8820000290870667},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7269999980926514},{"id":"https://openalex.org/keywords/language-documentation","display_name":"language documentation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8180000185966492},{"id":"https://openalex.org/keywords/connectionist-temporal-classification","display_name":"connectionist temporal classification","score":0.9779999852180481},{"id":"https://openalex.org/keywords/pitch-information","display_name":"pitch information","score":0.7020000219345093},{"id":"https://openalex.org/keywords/training-data-scaling","display_name":"training data scaling","score":0.5839999914169312}],"concepts":[{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7370666861534119},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.729059636592865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289069890975952},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6274729371070862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5863209366798401},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48899972438812256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48827075958251953},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4842767119407654},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.42817503213882446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817281126976013},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3603363037109375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.345832884311676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11193746328353882},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0721074640750885},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:HAL:halshs-01709648v4","doi":null,"is_oa":true,"landing_page_url":"https://shs.hal.science/halshs-01709648","pdf_url":"https://shs.hal.science/halshs-01709648v4/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://aclanthology.org/L18-1530","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:halshs-01709648v1","doi":null,"is_oa":true,"landing_page_url":"https://halshs.archives-ouvertes.fr/halshs-01709648","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://halshs.archives-ouvertes.fr/halshs-01709648","raw_type":"info:eu-repo/semantics/preprint"},{"id":"mag:2787760419","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/L18-1530.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"pmh:oai:HAL:halshs-01709648v4","doi":null,"is_oa":true,"landing_page_url":"https://shs.hal.science/halshs-01709648","pdf_url":"https://shs.hal.science/halshs-01709648v4/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://aclanthology.org/L18-1530","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8786586098","display_name":"RI: Small: Language Induction meets Language Documentation: Leveraging bilingual aligned audio for learning and preserving languages","funder_award_id":"1464553","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787760419.pdf","grobid_xml":"https://content.openalex.org/works/W2787760419.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2552454730"],"related_works":["https://openalex.org/W7160292279","https://openalex.org/W2773798130","https://openalex.org/W6925167106","https://openalex.org/W2972520202","https://openalex.org/W2087395764","https://openalex.org/W4385823505","https://openalex.org/W7097251514","https://openalex.org/W4404783379","https://openalex.org/W3171699967","https://openalex.org/W2941600164"],"abstract_inverted_index":{"Transcribing":[0],"speech":[1,10],"is":[2,93],"an":[3],"important":[4],"part":[5],"of":[6,25,65],"language":[7,44],"documentation,":[8],"yet":[9],"recognition":[11,88],"technology":[12,118],"has":[13],"not":[14],"been":[15],"widely":[16],"harnessed":[17],"to":[18,99,106,143],"aid":[19],"linguists.":[20],"We":[21,111],"explore":[22,51],"the":[23,31,63,85,113,120,129,140,144],"use":[24],"a":[26,43],"neural":[27],"network":[28],"architecture":[29],"with":[30],"connectionist":[32],"temporal":[33],"classification":[34],"loss":[35],"function":[36],"for":[37,71,102,109,123,153],"phonemic":[38,69,151],"and":[39,55,61,81,104,138,150],"tonal":[40,72,77],"transcription":[41],"in":[42,87,132],"documentation":[45],"setting.":[46],"In":[47],"this":[48,117],"framework,":[49],"we":[50],"jointly":[52],"modelling":[53,58],"phonemes":[54],"tones":[56],"versus":[57,68],"them":[59],"separately,":[60],"assess":[62],"importance":[64],"pitch":[66],"information":[67],"context":[70],"prediction.":[73],"Experiments":[74],"on":[75],"two":[76],"languages,":[78],"Yongning":[79,125],"Na":[80],"Eastern":[82],"Chatino,":[83,103],"show":[84,128],"changes":[86],"performance":[89],"as":[90],"training":[91],"data":[92],"scaled":[94],"from":[95,115],"10":[96],"minutes":[97,101,108],"up":[98,105],"50":[100],"224":[107],"Na.":[110],"discuss":[112],"findings":[114],"incorporating":[116],"into":[119],"linguistic":[121,154],"workflow":[122],"documenting":[124],"Na,":[126],"which":[127],"method's":[130],"promise":[131],"improving":[133],"efficiency,":[134],"minimizing":[135],"typographical":[136],"errors,":[137],"maintaining":[139],"transcription's":[141],"faithfulness":[142],"acoustic":[145],"signal,":[146],"while":[147],"highlighting":[148],"phonetic":[149],"facts":[152],"consideration.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2018-02-23T00:00:00"}
