{"id":"https://openalex.org/W1516533146","doi":"https://doi.org/10.21437/interspeech.2013-545","title":"TUNDRA: a multilingual corpus of found data for TTS research created with light supervision","display_name":"TUNDRA: a multilingual corpus of found data for TTS research created with light supervision","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W1516533146","doi":"https://doi.org/10.21437/interspeech.2013-545","mag":"1516533146"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-545","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca, Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"O. Watts","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000153508","display_name":"Yoshitaka Mamiya","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Y. Mamiya","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038722127","display_name":"Mircea Giurgiu","orcid":"https://orcid.org/0009-0007-9789-6083"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"M. Giurgiu","raw_affiliation_strings":["Technical University of Cluj-Napoca, Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084488961","display_name":"Robert A. Clark","orcid":"https://orcid.org/0000-0002-4892-3619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert A. J. Clark","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5018126799"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":7.4158,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96780021,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2331","last_page":"2335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.9951000213623047,"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":0.8324933648109436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6986682415008545},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6415888071060181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6107529997825623},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5721291899681091},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4695865511894226},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4566795229911804},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.26950785517692566},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07316553592681885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324933648109436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6986682415008545},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6415888071060181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6107529997825623},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5721291899681091},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4695865511894226},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4566795229911804},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26950785517692566},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07316553592681885}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2013-545","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","pdf_url":"https://www.research.ed.ac.uk/en/publications/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.250","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2013/IS131055.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.998.613","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.998.613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ed.ac.uk/portal/files/14561813/Stan_Watts_et_al_2013_TUNDRA_a_multilingual_corpus_of_found_data_for_TTS_research_created_with_light_supervision.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Stan, A, Watts, O, Mamiya, Y, Giurgiu, M, Clark, R A J, Yamagishi, J & King, S 2013, TUNDRA: a multilingual corpus of found data for TTS research created with light supervision. in INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association : Lyon, France, August 25-29, 2013. pp. 2331-2335. < http://www.isca-speech.org/archive/interspeech_2013/i13_2331.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","pdf_url":"https://www.research.ed.ac.uk/en/publications/6f8e714a-f0fe-4ce0-a404-d2ee99c3a34c","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1516533146.pdf","grobid_xml":"https://content.openalex.org/works/W1516533146.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W10731371","https://openalex.org/W165878654","https://openalex.org/W1245895196","https://openalex.org/W1517939602","https://openalex.org/W2026490135","https://openalex.org/W2054442733","https://openalex.org/W2096815491","https://openalex.org/W2099062766","https://openalex.org/W2105961775","https://openalex.org/W2107457864","https://openalex.org/W2128066925","https://openalex.org/W2145880678","https://openalex.org/W2156513557","https://openalex.org/W2163925746","https://openalex.org/W2165159713","https://openalex.org/W2170980774","https://openalex.org/W2181715383","https://openalex.org/W2250270880","https://openalex.org/W2294232014","https://openalex.org/W2296111744","https://openalex.org/W2406986214","https://openalex.org/W2544480456","https://openalex.org/W3177989406"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2361861616","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W187174317","https://openalex.org/W1835173349","https://openalex.org/W23627563"],"abstract_inverted_index":{"Simple4All":[0],"Tundra":[1],"(version":[2],"1.0)":[3],"is":[4],"the":[5,50,74,92,102,127],"first":[6],"release":[7],"of":[8,25,29,49,60,73,85],"a":[9,44,70,82],"standardised":[10],"multilingual":[11,131],"corpus":[12,23,51],"designed":[13],"for":[14,114],"text-to-speech":[15,109],"re-search":[16],"with":[17,43],"imperfect":[18,135],"or":[19,119],"found":[20,137],"data.":[21],"The":[22],"consists":[24],"approximately":[26],"60":[27],"hours":[28],"speech":[30],"data":[31,75,141],"from":[32],"audiobooks":[33],"in":[34,126],"14":[35],"languages,":[36],"as":[37,39,79,81],"well":[38,80],"utterance-level":[40],"alignments":[41],"obtained":[42],"lightly-supervised":[45],"process.":[46],"Future":[47],"versions":[48],"will":[52,62],"include":[53],"finer-grained":[54],"alignment":[55],"and":[56,96],"prosodic":[57],"annotation,":[58],"all":[59,115],"which":[61],"be":[63],"made":[64],"freely":[65],"available.":[66],"This":[67],"paper":[68],"gives":[69],"gen-eral":[71],"outline":[72],"collected":[76],"so":[77],"far,":[78],"detailed":[83],"description":[84],"how":[86],"this":[87],"has":[88],"been":[89,112],"done,":[90],"emphasizing":[91],"mini-mal":[93],"language-specific":[94],"knowledge":[95],"manual":[97],"intervention":[98],"used":[99],"to":[100],"compile":[101],"corpus.":[103],"To":[104],"demonstrate":[105],"its":[106],"potential":[107],"use,":[108],"systems":[110],"have":[111],"built":[113],"languages":[116],"using":[117],"unsu-pervised":[118],"lightly":[120],"supervised":[121],"methods,":[122],"also":[123],"briefly":[124],"presented":[125],"paper.":[128],"Index":[129],"Terms:":[130],"corpus,":[132],"light":[133],"supervision,":[134],"data,":[136,138],"text-to-speech,":[139],"audiobook":[140]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}