{"id":"https://openalex.org/W2404162686","doi":"https://doi.org/10.21437/interspeech.2012-656","title":"Perceptual foundations for naturalistic variability in the prosody of synthetic speech","display_name":"Perceptual foundations for naturalistic variability in the prosody of synthetic speech","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2404162686","doi":"https://doi.org/10.21437/interspeech.2012-656","mag":"2404162686"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-656","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5014998350","display_name":"Nanette Veilleux","orcid":"https://orcid.org/0000-0001-9025-8969"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nanette Veilleux","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103089213","display_name":"Jonathan Barnes","orcid":"https://orcid.org/0000-0002-9264-2363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Barnes","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023638693","display_name":"Alejna Brugos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alejna Brugos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081406386","display_name":"Stefanie Shattuck\u2010Hufnagel","orcid":"https://orcid.org/0000-0003-0991-5541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefanie Shattuck-Hufnagel","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014998350"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32764205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2534","last_page":"2537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998999834060669,"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/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/T12031","display_name":"Speech and dialogue systems","score":0.9934999942779541,"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":0.6983304619789124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6762842535972595},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6643093824386597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6206521391868591},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.49662619829177856},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4447616636753082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4419418275356293},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4393397569656372},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43050622940063477},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41570520401000977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35268455743789673},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16471463441848755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1562357246875763},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08829337358474731}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6983304619789124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762842535972595},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6643093824386597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6206521391868591},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.49662619829177856},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4447616636753082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4419418275356293},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4393397569656372},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43050622940063477},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41570520401000977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35268455743789673},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16471463441848755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1562357246875763},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08829337358474731},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-656","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W173888401","https://openalex.org/W1992850358","https://openalex.org/W2060802109","https://openalex.org/W2089533914","https://openalex.org/W2118092583","https://openalex.org/W2129286383","https://openalex.org/W2158848311","https://openalex.org/W2330299933","https://openalex.org/W3216401400"],"related_works":["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","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4],"the":[5,41,49,72],"Tonal":[6],"Center":[7],"of":[8,48,75,78,86,98],"Gravity":[9],"is":[10],"a":[11,34,54,76,90,96,111],"better":[12],"classifier":[13],"than":[14],"F0":[15,36,42,51,81],"Turning":[16],"Points":[17],"for":[18,64],"at":[19],"least":[20],"two":[21],"contrastively":[22],"timed":[23],"pitch":[24],"accents":[25],"in":[26,56,84,108,117],"American":[27],"English":[28],"intonation":[29],"contours.":[30],"Within":[31],"this":[32,102],"framework,":[33],"binary":[35,99],"weighting":[37,100],"function":[38],"derived":[39],"from":[40],"contour":[43,52,82],"can":[44,70],"be":[45,106],"used":[46],"instead":[47],"natural":[50],"without":[53],"degradation":[55],"discrimination":[57],"performance.":[58],"This":[59],"success":[60],"has":[61],"important":[62],"implications":[63],"speech":[65,118],"synthesis.":[66,119],"Just":[67],"as":[68,110],"we":[69],"capture":[71],"functional":[73],"equivalence":[74],"multitude":[77],"auditorily":[79],"distinct":[80],"shapes":[83],"terms":[85],"their":[87],"mapping":[88,104],"to":[89,113],"single":[91],"parameter":[92],"(the":[93],"TCoG)":[94],"via":[95],"set":[97],"functions,":[101],"same":[103],"could":[105],"run":[107],"reverse":[109],"source":[112],"generate":[114],"natural-sounding":[115],"variability":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
