{"id":"https://openalex.org/W3208065268","doi":"https://doi.org/10.1109/sped53181.2021.9587438","title":"The MARA corpus: Expressivity in end-to-end TTS systems using synthesised speech data","display_name":"The MARA corpus: Expressivity in end-to-end TTS systems using synthesised speech data","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3208065268","doi":"https://doi.org/10.1109/sped53181.2021.9587438","mag":"3208065268"},"language":"en","primary_location":{"id":"doi:10.1109/sped53181.2021.9587438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016558880","display_name":"Be\u00e1ta L\u0151rincz","orcid":"https://orcid.org/0000-0002-7728-5863"},"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"]},{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Beata Lorincz","raw_affiliation_strings":["Babe\u015f-Bolyai University, Cluj-Napoca, Romania","Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Babe\u015f-Bolyai University, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043037309","display_name":"Maria Nu\u021bu","orcid":"https://orcid.org/0000-0002-3215-5723"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]},{"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":"Maria Nutu","raw_affiliation_strings":["Babe\u015f-Bolyai University, Cluj-Napoca, Romania","Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Babe\u015f-Bolyai University, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","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":"Mircea Giurgiu","raw_affiliation_strings":["Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018126799"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69361425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"26","issue":null,"first_page":"85","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9991999864578247,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8520110845565796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6429030895233154},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5467697978019714},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.49814391136169434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48986026644706726},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4655863344669342},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3560801148414612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3253953456878662},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17199629545211792},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.10454955697059631}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8520110845565796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6429030895233154},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5467697978019714},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.49814391136169434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48986026644706726},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4655863344669342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3560801148414612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3253953456878662},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17199629545211792},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.10454955697059631}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped53181.2021.9587438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W344150399","https://openalex.org/W1500331947","https://openalex.org/W1993267429","https://openalex.org/W2107860279","https://openalex.org/W2153914468","https://openalex.org/W2163925746","https://openalex.org/W2182214061","https://openalex.org/W2471520273","https://openalex.org/W2598638573","https://openalex.org/W2605320104","https://openalex.org/W2738884019","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2884607399","https://openalex.org/W2885800352","https://openalex.org/W2890606114","https://openalex.org/W2904459034","https://openalex.org/W2914037612","https://openalex.org/W2941649920","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W6611766843","https://openalex.org/W6736204136","https://openalex.org/W6741399199","https://openalex.org/W6746700228","https://openalex.org/W6750489868","https://openalex.org/W6753540710","https://openalex.org/W6755300632"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W2338806053","https://openalex.org/W3163634122","https://openalex.org/W2110442089","https://openalex.org/W3119482857","https://openalex.org/W2919182614","https://openalex.org/W4385571610"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,69,74,91,102,125,129,137,149],"MARA":[4,70],"corpus,":[5,71],"a":[6,21,46],"large":[7],"expressive":[8,104,114],"Romanian":[9],"speech":[10,78,84,131],"corpus":[11],"containing":[12],"over":[13],"11":[14],"hours":[15],"of":[16,76,101,113,128],"high-quality":[17],"data":[18,26,81,89,115,132],"recorded":[19],"by":[20,45,136],"professional":[22],"female":[23],"speaker.":[24],"The":[25,40,87,118],"is":[27,43,133],"orthographically":[28],"transcribed,":[29],"manually":[30],"segmented":[31],"at":[32,38],"utterance":[33],"level":[34],"and":[35,66,95,120,140,152],"semi-automatically":[36],"aligned":[37],"phone-level.":[39],"associated":[41],"text":[42,53],"processed":[44],"complete":[47],"linguistic":[48],"feature":[49],"extractor":[50],"composed":[51],"of:":[52],"normalisation,":[54],"phonetic":[55],"transcription,":[56],"syllabification,":[57],"lexical":[58],"stress":[59],"assignment,":[60],"lemma":[61],"extraction,":[62],"part-of-speech":[63],"tagging,":[64],"chunking":[65],"dependency":[67],"parsing.Using":[68],"we":[72],"evaluate":[73],"use":[75],"synthesised":[77,88,130],"as":[79],"training":[80],"in":[82],"end-to-end":[83],"synthesis":[85,138],"systems.":[86],"copies":[90],"original":[92],"phone":[93],"duration":[94],"F":[96],"<inf":[97],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[98],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[99],"patterns":[100],"most":[103],"utterances":[105],"from":[106],"MARA.":[107],"Five":[108],"systems":[109],"with":[110],"different":[111],"sets":[112],"are":[116,146],"trained.":[117],"objective":[119],"subjective":[121],"results":[122],"show":[123],"that":[124,141],"low":[126],"quality":[127],"averaged":[134],"out":[135],"network,":[139],"no":[142],"statistically":[143],"significant":[144],"differences":[145],"found":[147],"between":[148],"systems\u2019":[150],"expressivity":[151],"naturalness":[153],"evaluations.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}