{"id":"https://openalex.org/W73525854","doi":"https://doi.org/10.21437/interspeech.2007-222","title":"Increasing prosodic variability of text-to-speech synthesizers","display_name":"Increasing prosodic variability of text-to-speech synthesizers","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W73525854","doi":"https://doi.org/10.21437/interspeech.2007-222","mag":"73525854"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-222","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"G\u00e9za N\u00e9meth","raw_affiliation_strings":["Budapest Univ. of Technology & Economics"],"affiliations":[{"raw_affiliation_string":"Budapest Univ. of Technology & Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029130666","display_name":"M\u00e1rk F\u00e9k","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"M\u00e1rk F\u00e9k","raw_affiliation_strings":["Budapest Univ. of Technology & Economics"],"affiliations":[{"raw_affiliation_string":"Budapest Univ. of Technology & Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":["Budapest Univ. of Technology & Economics"],"affiliations":[{"raw_affiliation_string":"Budapest Univ. of Technology & Economics","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069988513"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.00700438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.996999979019165,"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/T12031","display_name":"Speech and dialogue systems","score":0.9962999820709229,"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/prosody","display_name":"Prosody","score":0.897803544998169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419203519821167},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.725503146648407},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.704585075378418},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6462157964706421},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6254836916923523},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5899657607078552},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5186435580253601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5164316296577454},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48930618166923523},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4287906289100647},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.41906577348709106},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2936394512653351},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1437380015850067},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09542319178581238}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.897803544998169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419203519821167},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.725503146648407},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.704585075378418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6462157964706421},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6254836916923523},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5899657607078552},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5186435580253601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5164316296577454},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48930618166923523},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4287906289100647},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.41906577348709106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2936394512653351},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1437380015850067},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09542319178581238},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-222","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.611.7304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.611.7304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://speechlab.tmit.bme.hu/downloads/NemethFekCsapo-interspeech2007-paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W134844091","https://openalex.org/W2017291470","https://openalex.org/W2154280657","https://openalex.org/W3216401400","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2396586136","https://openalex.org/W1505084104","https://openalex.org/W2599935372","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051"],"abstract_inverted_index":{"The":[0,60,93],"lack":[1],"of":[2,33,62,77,89,98,109],"prosody":[3,26,61,76],"variation":[4],"in":[5,28],"text-to-speech":[6],"systems":[7],"contributes":[8],"to":[9,24,47,73,85],"their":[10],"perceived":[11],"unnaturalness":[12],"when":[13],"synthesizing":[14],"extended":[15],"passages.":[16],"In":[17],"this":[18,29],"paper,":[19],"we":[20],"present":[21],"a":[22,71,99,106,127],"method":[23,125],"improve":[25],"generation":[27,97],"direction.":[30],"A":[31,113],"database":[32],"natural":[34,66],"sample":[35],"sentences":[36,40,58,120],"is":[37,52,68],"searched":[38],"for":[39],"having":[41],"similar":[42,57],"word":[43],"and":[44],"syllable":[45],"structure":[46],"the":[48,56,63,75,78,87,90,110,123],"input.":[49],"One":[50],"sentence":[51,67],"selected":[53,65],"randomly":[54,64],"from":[55],"found.":[59],"used":[69],"as":[70],"target":[72],"generate":[74],"synthetic":[79],"one.":[80],"An":[81],"experiment":[82],"was":[83,103],"conducted":[84],"determine":[86],"potential":[88],"proposed":[91,111,124],"method.":[92,112],"rule-based":[94,128],"pitch":[95],"contour":[96],"Hungarian":[100],"concatenative":[101],"synthesizer":[102],"replaced":[104],"by":[105,122],"semi-automatic":[107],"implementation":[108],"listening":[114],"test":[115],"showed":[116],"that":[117],"subjects":[118],"preferred":[119],"synthesized":[121],"over":[126],"solution.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
