{"id":"https://openalex.org/W3148525572","doi":"https://doi.org/10.21437/interspeech.2021-1435","title":"Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments","display_name":"Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3148525572","doi":"https://doi.org/10.21437/interspeech.2021-1435","mag":"3148525572"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1435","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1435","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/2104.00824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046329348","display_name":"Jordan Picone","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jordan Picone","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, United States","institution_ids":["https://openalex.org/I170201317"]}]},{"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":"last","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":["Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34188393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3660","last_page":"3664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802501916885376},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6795033812522888},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.648003339767456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5265253782272339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48186931014060974},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4651670455932617},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41612038016319275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38197124004364014},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2094554603099823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802501916885376},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6795033812522888},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.648003339767456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5265253782272339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48186931014060974},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4651670455932617},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41612038016319275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38197124004364014},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2094554603099823},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1435","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1435","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:2104.00824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00824","pdf_url":"https://arxiv.org/pdf/2104.00824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:3148525572","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2104.00824.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2104.00824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.00824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2104.00824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00824","pdf_url":"https://arxiv.org/pdf/2104.00824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3148525572.pdf","grobid_xml":"https://content.openalex.org/works/W3148525572.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2079692841","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2250357346","https://openalex.org/W2572670101","https://openalex.org/W2905961459","https://openalex.org/W2992454285","https://openalex.org/W2998284473","https://openalex.org/W3015877095","https://openalex.org/W3017568157","https://openalex.org/W3160275121","https://openalex.org/W3209383001"],"related_works":["https://openalex.org/W3198165100","https://openalex.org/W2762715843","https://openalex.org/W3092085609","https://openalex.org/W2884066185","https://openalex.org/W3032433061","https://openalex.org/W1974685450","https://openalex.org/W2756675017","https://openalex.org/W3031995935","https://openalex.org/W2991031117","https://openalex.org/W2566558946","https://openalex.org/W3118580427","https://openalex.org/W3213618310","https://openalex.org/W2250739201","https://openalex.org/W3147984406","https://openalex.org/W3095845993","https://openalex.org/W3043665049","https://openalex.org/W3197233518","https://openalex.org/W3054645415","https://openalex.org/W3118006758","https://openalex.org/W3039018004"],"abstract_inverted_index":{"There":[0,15],"is":[1,16,30,84,94],"growing":[2],"interest":[3,18],"in":[4,11,19,62,79,86],"ASR":[5],"systems":[6,43,102,131],"that":[7,36],"can":[8,37],"recognize":[9],"phones":[10],"a":[12,31,49,73,95],"language-independent":[13],"fashion.":[14],"additionally":[17],"building":[20],"language":[21,66,75],"technologies":[22],"for":[23,98,137],"low-resource":[24],"and":[25,44,59,114],"endangered":[26,64],"languages.":[27],"However,":[28],"there":[29],"paucity":[32],"of":[33,55,88,126],"realistic":[34],"data":[35],"be":[38],"used":[39,117],"to":[40,118],"test":[41],"such":[42],"technologies.":[45],"This":[46,109],"paper":[47,110],"presents":[48,123],"publicly":[50],"available,":[51],"phonetically":[52],"transcribed":[53,85],"corpus":[54],"2255":[56],"utterances":[57],"(words":[58],"short":[60],"phrases)":[61],"the":[63,82,112,115,133],"Tangkhulic":[65],"East":[67],"Tusom":[68],"(no":[69],"ISO":[70],"639-3":[71],"code),":[72],"Tibeto-Burman":[74],"variety":[76],"spoken":[77],"mostly":[78],"India.":[80],"Because":[81],"dataset":[83,113,134],"terms":[87],"phones,":[89],"rather":[90],"than":[91,103],"phonemes,":[92],"it":[93],"better":[96],"match":[97],"universal":[99,128],"phone":[100,129],"recognition":[101,130],"many":[104],"larger":[105],"(phonemically":[106],"transcribed)":[107],"datasets.":[108],"describes":[111],"methodology":[116],"produce":[119],"it.":[120],"It":[121],"further":[122],"basic":[124],"benchmarks":[125],"state-of-the-art":[127],"on":[132],"as":[135],"baselines":[136],"future":[138],"experiments.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}