{"id":"https://openalex.org/W2891080700","doi":"https://doi.org/10.1109/icassp.2018.8461719","title":"Measuring the Effect of Linguistic Resources on Prosody Modeling for Speech Synthesis","display_name":"Measuring the Effect of Linguistic Resources on Prosody Modeling for Speech Synthesis","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891080700","doi":"https://doi.org/10.1109/icassp.2018.8461719","mag":"2891080700"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["IBM Research AI, TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raul Fernandez","raw_affiliation_strings":["IBM Research AI, TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Research AI, TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1610 3017","issue":null,"first_page":"5114","last_page":"5118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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":0.9973999857902527,"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":0.9081000089645386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912670373916626},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.659839391708374},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5860468149185181},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5700469017028809},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5367720127105713},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5235995054244995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.521971583366394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5134657025337219},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.48081815242767334},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4782516062259674},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44424429535865784},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42044365406036377},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.2274649739265442},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15454289317131042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09348580241203308},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0930338203907013}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9081000089645386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912670373916626},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.659839391708374},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5860468149185181},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5700469017028809},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5367720127105713},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5235995054244995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.521971583366394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134657025337219},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.48081815242767334},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4782516062259674},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44424429535865784},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42044365406036377},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2274649739265442},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15454289317131042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09348580241203308},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0930338203907013},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1973581551","https://openalex.org/W2137371951","https://openalex.org/W2143777890","https://openalex.org/W2396931946","https://openalex.org/W2401335838","https://openalex.org/W2531207078","https://openalex.org/W2604184139","https://openalex.org/W2745644908","https://openalex.org/W2749074593","https://openalex.org/W2963403664","https://openalex.org/W4385245566","https://openalex.org/W6681282213","https://openalex.org/W6712324455","https://openalex.org/W6713087852","https://openalex.org/W6725896364","https://openalex.org/W6728267052","https://openalex.org/W6736356763","https://openalex.org/W6739901393","https://openalex.org/W6759822529"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W3149582125","https://openalex.org/W2465421051","https://openalex.org/W1984347656","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663"],"abstract_inverted_index":{"The":[0],"generation":[1],"of":[2,12,26,50,86,94,106,116],"natural":[3],"and":[4,35,129],"expressive":[5],"prosodic":[6],"contours":[7],"is":[8],"an":[9],"important":[10],"component":[11],"a":[13,27,39,66,70,87,92,103],"text-to-speech":[14],"(TTS)":[15],"system":[16,68,89],"which,":[17],"in":[18,69],"most":[19],"classical":[20],"architectures,":[21],"relies":[22],"on":[23,120],"the":[24,51,83,114,118,131],"existence":[25],"text-analysis":[28],"processor":[29],"that":[30,99],"can":[31,45],"extract":[32],"prosody-predictive":[33],"features":[34,44,57],"pass":[36],"them":[37],"to":[38,54,102],"statistical":[40],"learning":[41],"model.":[42],"These":[43],"range":[46],"from":[47],"basic":[48],"properties":[49],"input":[52,121],"string":[53],"rich":[55,107],"high-level":[56],"which":[58],"may":[59],"not":[60],"be":[61],"always":[62],"available":[63],"when":[64],"developing":[65],"TTS":[67],"new":[71],"language":[72],"with":[73],"sparse":[74],"computational":[75],"resources.":[76,108],"In":[77],"this":[78],"work":[79],"we":[80],"investigate":[81],"how":[82],"prosody":[84,124],"model":[85],"speech-synthesis":[88],"performs":[90],"as":[91],"function":[93],"different":[95],"predictive":[96],"feature":[97],"sets":[98],"assume":[100],"access":[101],"certain":[104],"amount":[105],"We":[109],"investigate,":[110],"using":[111],"objective":[112],"metrics,":[113],"effect":[115],"relaxing":[117],"assumptions":[119],"representations":[122],"for":[123,126,134],"prediction":[125],"5":[127],"languages,":[128],"evaluate":[130],"perceptual":[132],"implications":[133],"US":[135],"English.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}