{"id":"https://openalex.org/W2399816321","doi":"https://doi.org/10.21437/interspeech.2011-820","title":"Open source voice creation toolkit for the MARY TTS platform","display_name":"Open source voice creation toolkit for the MARY TTS platform","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2399816321","doi":"https://doi.org/10.21437/interspeech.2011-820","mag":"2399816321"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-820","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5110281069","display_name":"Marc L. Schr\u00f6der","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marc Schr\u00f6der","raw_affiliation_strings":["DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Allemagne)"],"affiliations":[{"raw_affiliation_string":"DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Allemagne)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008628120","display_name":"Marcela Charfuel\u00e0n","orcid":"https://orcid.org/0009-0005-6886-0415"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcela Charfuelan","raw_affiliation_strings":["DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Allemagne)"],"affiliations":[{"raw_affiliation_string":"DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Allemagne)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091847956","display_name":"Sathish Pammi","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sathish Pammi","raw_affiliation_strings":["DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Allemagne)"],"affiliations":[{"raw_affiliation_string":"DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Allemagne)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004840801","display_name":"Ingmar Steiner","orcid":"https://orcid.org/0000-0001-6415-5915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingmar Steiner","raw_affiliation_strings":["PAROLE - Analysis, perception and recognition of speech (France)"],"affiliations":[{"raw_affiliation_string":"PAROLE - Analysis, perception and recognition of speech (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110281069"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":5.2629,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95682786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3253","last_page":"3256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9675999879837036,"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/computer-science","display_name":"Computer science","score":0.8280184268951416},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.7303203344345093},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6209471225738525},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5844356417655945},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5758510231971741},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5639960169792175},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4924977719783783},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48535576462745667},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4437513053417206},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.41657134890556335},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3843121826648712},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.352841317653656},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.33835357427597046},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32253122329711914},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22105777263641357},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17359623312950134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.15254881978034973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11618861556053162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280184268951416},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.7303203344345093},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6209471225738525},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5844356417655945},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5758510231971741},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5639960169792175},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4924977719783783},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48535576462745667},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4437513053417206},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.41657134890556335},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3843121826648712},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.352841317653656},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33835357427597046},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32253122329711914},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22105777263641357},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17359623312950134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.15254881978034973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11618861556053162},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-820","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W90422898","https://openalex.org/W1870008521","https://openalex.org/W2130890537","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W2093262417","https://openalex.org/W2123131699","https://openalex.org/W913131694","https://openalex.org/W650116260","https://openalex.org/W2378329187","https://openalex.org/W4390790060","https://openalex.org/W2134191509","https://openalex.org/W1603423477","https://openalex.org/W3209454962","https://openalex.org/W1964405022"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,123],"open":[4],"source":[5],"voice":[6,64],"creation":[7,12,65,137],"toolkit":[8,32,66,116,145],"that":[9,102],"supports":[10],"the":[11,20,41,51,80,104,132,136,144],"of":[13,131,138,150],"unit":[14],"selection":[15],"and":[16,53,121,146],"HMM-based":[17],"voices,":[18],"for":[19,24,107,129],"MARY":[21,46],"(Modular":[22],"Architecture":[23],"Research":[25],"on":[26,76],"speech":[27,77],"Synthesis)":[28],"TTS":[29],"platform.":[30],"The":[31,63,115],"can":[33],"be":[34,71],"easily":[35],"employed":[36],"to":[37,59,70,95,112],"create":[38],"voices":[39],"in":[40,119,135],"languages":[42],"already":[43],"supported":[44],"by":[45,73],"TTS,":[47],"but":[48],"also":[49],"provides":[50],"tools":[52],"generic":[54],"reusable":[55,100],"run-time":[56],"system":[57],"modules":[58],"add":[60],"new":[61],"languages.":[62],"is":[67,117],"mainly":[68],"intended":[69],"used":[72],"research":[74],"groups":[75],"technology":[78,91,101],"throughout":[79],"world,":[81],"notably":[82],"those":[83],"who":[84],"do":[85],"not":[86],"have":[87],"their":[88],"own":[89],"pre-existing":[90],"yet.":[92],"We":[93,142],"try":[94],"provide":[96],"them":[97],"with":[98],"a":[99,139,148],"lowers":[103],"entrance":[105],"barrier":[106],"them,":[108],"making":[109],"it":[110],"easier":[111],"get":[113],"started.":[114],"developed":[118],"Java":[120],"includes":[122],"intuitive":[124],"Graphical":[125],"User":[126],"Interface":[127],"(GUI)":[128],"most":[130],"common":[133],"tasks":[134],"synthetic":[140],"voice.":[141],"present":[143],"discuss":[147],"number":[149],"interoperability":[151],"issues.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
