{"id":"https://openalex.org/W2399755580","doi":"https://doi.org/10.21437/interspeech.2015-130","title":"Using automatic stress extraction from audio for improved prosody modelling in speech synthesis","display_name":"Using automatic stress extraction from audio for improved prosody modelling in speech synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2399755580","doi":"https://doi.org/10.21437/interspeech.2015-130","mag":"2399755580"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-130","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5043901293","display_name":"Gy\u00f6rgy Szasz\u00e1k","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":true,"raw_author_name":"Gy\u00f6rgy Szasz\u00e1k","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032873613","display_name":"Andr\u00e1s Beke","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":"Andr\u00e1s Beke","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109853981","display_name":"G\u00e1bor Olaszy","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":"G\u00e1bor Olaszy","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101783073","display_name":"B\u00e1lint T\u00f3th","orcid":"https://orcid.org/0000-0003-1688-9089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00e1lint P\u00e1l T\u00f3th","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043901293"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":1.25720366,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90640656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2227","last_page":"2231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9991000294685364,"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":0.9976999759674072,"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":0.766985297203064},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7514695525169373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6613715887069702},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6291653513908386},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5987393260002136},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5712133646011353},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5673041939735413},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.48626744747161865},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43854543566703796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4343263506889343},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42419394850730896},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4234091639518738},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41992366313934326},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.29902082681655884},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12285348773002625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766985297203064},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7514695525169373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6613715887069702},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6291653513908386},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5987393260002136},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5712133646011353},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5673041939735413},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.48626744747161865},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43854543566703796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343263506889343},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42419394850730896},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4234091639518738},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41992366313934326},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.29902082681655884},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12285348773002625},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-130","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W107303030","https://openalex.org/W115591185","https://openalex.org/W178114869","https://openalex.org/W285815010","https://openalex.org/W1550374377","https://openalex.org/W1581480663","https://openalex.org/W1589081167","https://openalex.org/W1608101656","https://openalex.org/W1963627370","https://openalex.org/W2004415003","https://openalex.org/W2074817945","https://openalex.org/W2085628288","https://openalex.org/W2541777010"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W2161314515","https://openalex.org/W2550171623","https://openalex.org/W2036933852","https://openalex.org/W1987021544","https://openalex.org/W2014684632","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Generating":[0],"proper":[1],"and":[2,107,129,171],"natural":[3],"sounding":[4],"prosody":[5],"is":[6,23,61,96],"one":[7],"of":[8,12,26,104,114,124,163,174,186],"the":[9,24,122,125,136,148,172,175,187],"key":[10],"interests":[11],"today\u2019s":[13],"speech":[14,30,117],"synthesis":[15],"research.":[16],"An":[17],"important":[18],"factor":[19],"in":[20,183],"this":[21],"effort":[22],"availability":[25],"a":[27,39,42,116,130,143,161,193],"precisely":[28],"labelled":[29],"corpus":[31,118],"with":[32,135,152],"adequate":[33],"prosodic":[34,184],"stress":[35,89,105,126,153],"marking.":[36],"Obtaining":[37],"such":[38],"labelling":[40,75,103],"constitutes":[41],"huge":[43],"effort,":[44],"whereas":[45],"interannotator":[46],"agreement":[47],"scores":[48],"are":[49,140],"usually":[50],"found":[51],"far":[52],"below":[53],"100%.":[54],"Stress":[55],"marking":[56,154],"based":[57,91],"on":[58,93,147],"phonetic":[59],"transcription":[60],"an":[62,73,85,100,180],"alternative,":[63],"but":[64,151],"yields":[65],"even":[66],"poorer":[67],"quality":[68],"than":[69],"human":[70],"annotation.":[71],"Applying":[72],"automatic":[74,86],"may":[76],"help":[77],"overcoming":[78],"these":[79],"difficulties.":[80],"The":[81,166],"current":[82],"paper":[83],"presents":[84],"approach":[87],"for":[88],"detection":[90,127],"purely":[92],"audio,":[94],"which":[95],"used":[97],"to":[98,110,142],"derive":[99],"automatic,":[101],"layered":[102],"events":[106],"link":[108],"them":[109],"syllables.":[111],"For":[112],"proof":[113],"concept,":[115],"was":[119,133],"extended":[120,137],"by":[121],"output":[123],"algorithm":[128],"HMM-TTS":[131],"system":[132],"trained":[134,146],"corpus.":[138],"Results":[139,178],"compared":[141],"baseline":[144],"system,":[145],"same":[149],"database,":[150],"obtained":[155],"from":[156],"textual":[157],"transcripts":[158],"after":[159],"applying":[160],"set":[162],"linguistic":[164],"rules.":[165],"evaluation":[167],"includes":[168],"CMOS":[169],"tests":[170],"analysis":[173],"decision":[176],"trees.":[177],"show":[179],"overall":[181],"improvement":[182],"properties":[185],"synthesized":[188],"speech.":[189],"Subjective":[190],"ratings":[191],"reveal":[192],"voice":[194],"perceived":[195],"as":[196],"more":[197],"natural.":[198]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}