{"id":"https://openalex.org/W2765242664","doi":"https://doi.org/10.1145/3131785.3131835","title":"Contour","display_name":"Contour","publication_year":2017,"publication_date":"2017-10-20","ids":{"openalex":"https://openalex.org/W2765242664","doi":"https://doi.org/10.1145/3131785.3131835","mag":"2765242664"},"language":"en","primary_location":{"id":"doi:10.1145/3131785.3131835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3131785.3131835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Publication of the 30th Annual ACM Symposium on User Interface Software and Technology","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/A5025645387","display_name":"Yuanyi Fan","orcid":"https://orcid.org/0000-0003-2009-2523"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuan-Yi Fan","raw_affiliation_strings":["I.AM+, LLC, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"I.AM+, LLC, Los Angeles, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485056","display_name":"Soyoung Shin","orcid":"https://orcid.org/0000-0002-8073-6768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soyoung Shin","raw_affiliation_strings":["I.AM+, LLC, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"I.AM+, LLC, Los Angeles, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078076851","display_name":"Vids Samanta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vids Samanta","raw_affiliation_strings":["I.AM+, LLC, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"I.AM+, LLC, Los Angeles, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025645387"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58552405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9977999925613403,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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":0.783035159111023},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7344868183135986},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.6161924600601196},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5849429965019226},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5633763074874878},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5246132612228394},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5057387351989746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5051608681678772},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37635359168052673},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34830066561698914},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.278594970703125},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20152223110198975},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12101981043815613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783035159111023},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7344868183135986},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.6161924600601196},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5849429965019226},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5633763074874878},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5246132612228394},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5057387351989746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5051608681678772},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37635359168052673},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34830066561698914},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.278594970703125},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20152223110198975},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12101981043815613},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3131785.3131835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3131785.3131835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Publication of the 30th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1781518572","https://openalex.org/W2058733260","https://openalex.org/W2096429026","https://openalex.org/W2535255545","https://openalex.org/W2737697117","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3203313352","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W2587342322"],"abstract_inverted_index":{"Voice":[0],"assistant":[1],"technology":[2],"has":[3],"expanded":[4],"the":[5,39,51,99,104,113,122,141],"design":[6,20,137],"space":[7],"for":[8,67],"voice-activated":[9],"consumer":[10],"products":[11],"and":[12,48,70,118,134],"audio-centric":[13],"user":[14,83,145],"experience.":[15],"To":[16,97],"navigate":[17],"this":[18],"emerging":[19],"space,":[21],"Speech":[22],"Synthesis":[23],"Markup":[24],"Language":[25],"(SSML)":[26],"provides":[27],"a":[28,63,82],"standard":[29],"to":[30,84,131],"characterize":[31],"synthetic":[32],"speech":[33],"based":[34,128],"on":[35,129],"parametric":[36,114],"control":[37],"of":[38,62,136,144],"prosody":[40],"elements,":[41],"i.e.":[42],"pitch,":[43],"rate,":[44],"volume,":[45],"contour,":[46],"range,":[47],"duration.":[49],"However,":[50],"existing":[52],"voice":[53,93],"assistants":[54],"utilizing":[55],"Text-to-Speech":[56],"(TTS)":[57],"lack":[58],"expressiveness.":[59],"The":[60],"need":[61],"new":[64,100,123],"production":[65,147],"workflow":[66,101,124],"more":[68,126],"efficient":[69,127],"emotional":[71,90],"audio":[72],"content":[73,87],"using":[74,92],"TTS":[75],"is":[76,95,110,125],"discussed.":[77],"A":[78],"prototype":[79],"that":[80],"allows":[81],"produce":[85],"TTS-based":[86],"in":[88],"any":[89],"tone":[91],"input":[94],"presented.":[96],"evaluate":[98],"enabled":[102],"by":[103],"prototype,":[105],"an":[106],"initial":[107],"comparative":[108],"study":[109],"conducted":[111],"against":[112],"approach.":[115],"Preliminary":[116],"quantitative":[117],"qualitative":[119],"results":[120],"suggest":[121],"time":[130],"complete":[132],"tasks":[133],"number":[135],"iterations,":[138],"while":[139],"maintaining":[140],"same":[142],"level":[143],"preferred":[146],"quality.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2017-11-10T00:00:00"}
