{"id":"https://openalex.org/W2396181451","doi":"https://doi.org/10.21437/interspeech.2015-370","title":"Data-driven foot-based intonation generator for text-to-speech synthesis","display_name":"Data-driven foot-based intonation generator for text-to-speech synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2396181451","doi":"https://doi.org/10.21437/interspeech.2015-370","mag":"2396181451"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-370","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-370","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":"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/A5070345621","display_name":"Mahsa Sadat Elyasi Langarani","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahsa Sadat Elyasi Langarani","raw_affiliation_strings":["Oregon Health & Science University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041808115","display_name":"Jan P. H. van Santen","orcid":"https://orcid.org/0000-0003-3245-5301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan van Santen","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014830287","display_name":"Seyed Hamidreza Mohammadi","orcid":"https://orcid.org/0000-0002-6892-9241"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Hamidreza Mohammadi","raw_affiliation_strings":["Oregon Health & Science University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066668295","display_name":"Alexander Kain","orcid":"https://orcid.org/0000-0001-5807-9311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Kain","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.823,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75622913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1596","last_page":"1600"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9948999881744385,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9930999875068665,"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":0.7330744862556458},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.7218730449676514},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7147917747497559},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7011954188346863},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.6790859699249268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6612460017204285},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6338700652122498},{"id":"https://openalex.org/keywords/foot","display_name":"Foot (prosody)","score":0.5515204071998596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5390400886535645},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5334610939025879},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5261827707290649},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.49463769793510437},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.47705331444740295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38738158345222473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32185661792755127},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07500854134559631},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07028853893280029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330744862556458},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.7218730449676514},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7147917747497559},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7011954188346863},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.6790859699249268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6612460017204285},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6338700652122498},{"id":"https://openalex.org/C115076146","wikidata":"https://www.wikidata.org/wiki/Q1651051","display_name":"Foot (prosody)","level":2,"score":0.5515204071998596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390400886535645},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5334610939025879},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5261827707290649},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.49463769793510437},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.47705331444740295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38738158345222473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32185661792755127},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07500854134559631},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07028853893280029},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-370","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-370","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":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W48178999","https://openalex.org/W67241699","https://openalex.org/W95152782","https://openalex.org/W133559434","https://openalex.org/W1499275966","https://openalex.org/W1525540417","https://openalex.org/W1599681080","https://openalex.org/W1600722501","https://openalex.org/W1965568387","https://openalex.org/W1966499249","https://openalex.org/W2005465272","https://openalex.org/W2031893063","https://openalex.org/W2039995614","https://openalex.org/W2048389584","https://openalex.org/W2057609679","https://openalex.org/W2081234301","https://openalex.org/W2093476462","https://openalex.org/W2101234009","https://openalex.org/W2125508626","https://openalex.org/W2141708418","https://openalex.org/W2396622277","https://openalex.org/W2561088501","https://openalex.org/W2888778920"],"related_works":["https://openalex.org/W4212971584","https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2381837697","https://openalex.org/W2474947928","https://openalex.org/W2332932563","https://openalex.org/W2530248338","https://openalex.org/W1489682032"],"abstract_inverted_index":{"We":[0,79,164],"propose":[1],"a":[2,38],"method":[3,52,83,124,169],"for":[4,8,54,131,141,172],"generating":[5,173],"F0":[6,176],"contours":[7,93],"text-tospeech":[9],"synthesis.":[10],"Training":[11],"speech":[12,158],"is":[13,187],"automatically":[14],"annotated":[15],"in":[16,67,109],"terms":[17],"of":[18,27,156],"feet,":[19],"with":[20,60,154],"features":[21],"indicating":[22],"start":[23],"and":[24,31,46,102,160,184],"end":[25],"times":[26],"syllables,":[28],"foot":[29,32],"position,":[30],"length.":[33],"During":[34,49],"training,":[35],"we":[36,146],"fit":[37],"foot-based":[39],"superpositional":[40],"intonation":[41],"model":[42],"comprising":[43],"accent":[44,57,76],"curves":[45,58],"phrase":[47],"curves.":[48],"synthesis,":[50],"the":[51,68,81,85,116,122,137,167],"searches":[53],"stored,":[55],"fitted":[56],"associated":[59],"feet":[61,66],"that":[62,155,166],"optimally":[63],"match":[64],"to-be-synthesized":[65],"feature":[69],"space,":[70],"while":[71],"minimizing":[72],"differences":[73],"between":[74],"successive":[75],"curve":[77],"heights.":[78],"tested":[80],"proposed":[82,123],"against":[84],"HMMbased":[86],"Speech":[87],"Synthesis":[88],"System":[89],"(HTS)":[90],"by":[91,95,115,121],"imposing":[92],"generated":[94,120],"these":[96],"two":[97],"methods":[98],"onto":[99],"natural":[100,157],"speech,":[101],"obtaining":[103],"quality":[104],"ratings.":[105],"Test":[106],"sets":[107],"varied":[108],"how":[110],"well":[111],"they":[112],"were":[113,125],"covered":[114],"training":[117,180],"data.":[118],"Contours":[119],"preferred":[126],"over":[127],"HTS-generated":[128],"contours,":[129,177],"especially":[130,178],"poorly-covered":[132],"test":[133,136],"items.":[134],"To":[135],"new":[138,168],"method\u2019s":[139],"usefulness":[140],"processing":[142],"marked-up":[143],"text":[144],"input,":[145],"compared":[147],"its":[148],"ability":[149],"to":[150],"convey":[151],"contrastive":[152],"stress":[153],"recordings,":[159],"found":[161],"no":[162],"difference.":[163],"conclude":[165],"holds":[170],"promise":[171],"comparatively":[174],"highquality":[175],"when":[179,185],"data":[181],"are":[182],"sparse":[183],"mark-up":[186],"required.":[188]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}