{"id":"https://openalex.org/W1984939577","doi":"https://doi.org/10.1109/ncc.2015.7084924","title":"Data-driven pause prediction for speech synthesis in storytelling style speech","display_name":"Data-driven pause prediction for speech synthesis in storytelling style speech","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W1984939577","doi":"https://doi.org/10.1109/ncc.2015.7084924","mag":"1984939577"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2015.7084924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2015.7084924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Twenty First National Conference on Communications (NCC)","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/A5089591716","display_name":"Parakrant Sarkar","orcid":"https://orcid.org/0000-0001-6505-3443"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parakrant Sarkar","raw_affiliation_strings":["School of Information Technology Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048234263","display_name":"K. Sreenivasa Rao","orcid":"https://orcid.org/0000-0002-2186-0419"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Sreenivasa Rao","raw_affiliation_strings":["School of Information Technology Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":3.1158,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92669179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.711114227771759},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.6846705675125122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.606848418712616},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5852689743041992},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5449184775352478},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4063088297843933},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11481234431266785},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.058173924684524536},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0546489953994751}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711114227771759},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6846705675125122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.606848418712616},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5852689743041992},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5449184775352478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4063088297843933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11481234431266785},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.058173924684524536},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0546489953994751},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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:10.1109/ncc.2015.7084924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2015.7084924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Twenty First National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W27689248","https://openalex.org/W162654330","https://openalex.org/W206501079","https://openalex.org/W1523135049","https://openalex.org/W1547742344","https://openalex.org/W1779549900","https://openalex.org/W1912504566","https://openalex.org/W2018715519","https://openalex.org/W2065483314","https://openalex.org/W2075170185","https://openalex.org/W2143777890","https://openalex.org/W2150612204","https://openalex.org/W2171121512","https://openalex.org/W2345703460","https://openalex.org/W2404279351","https://openalex.org/W2406409859","https://openalex.org/W2578321825","https://openalex.org/W2578832979","https://openalex.org/W3022351837","https://openalex.org/W4232371001","https://openalex.org/W6600088033","https://openalex.org/W6608501318","https://openalex.org/W6713700427","https://openalex.org/W6714053574","https://openalex.org/W6732119548","https://openalex.org/W6732215457","https://openalex.org/W6776921881","https://openalex.org/W7001192717"],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W3107474891","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W4321496520","https://openalex.org/W2293457016","https://openalex.org/W2794438528","https://openalex.org/W2249384744"],"abstract_inverted_index":{"In":[0,85,108,126],"the":[1,24,27,37,42,45,49,54,62,86,89,96,109,112,127,137,152,167,171],"storyteller":[2,58],"speech,":[3],"pauses":[4,43,63,113],"plays":[5],"a":[6,103,121,130,163],"significant":[7],"role":[8],"in":[9,26,44,57,166],"introducing":[10],"suspense":[11],"and":[12,22,39,60,72,147],"climax.":[13],"Pauses":[14],"are":[15,114,161],"used":[16],"to":[17,35,94,135,150],"emphasize":[18],"keywords,":[19],"emotion-salient":[20],"words":[21],"separate":[23],"phrases":[25],"utterance.":[28],"The":[29,155],"objective":[30,146],"of":[31,41,105,123],"this":[32],"work":[33],"is":[34,83,91,133],"predict":[36,136],"position":[38,98],"duration":[40,139],"synthesized":[46,168],"speech":[47,59,169],"from":[48],"text-to-speech":[50],"system.":[51],"We":[52,143],"analyzed":[53],"pause":[55,80,97,138],"patterns":[56],"classified":[61,115],"into":[64,116],"three":[65,78,117],"different":[66,118],"categories,":[67],"that":[68,159],"is,":[69],"short,":[70],"medium":[71],"long":[73],"pauses.":[74],"A":[75],"data":[76],"driven":[77],"stage":[79],"prediction":[81],"model":[82,90],"proposed.":[84],"first":[87],"stage,":[88,111,129],"built":[92],"properly":[93],"identify":[95],"within":[99],"an":[100],"utterance":[101],"using":[102,120,170],"set":[104,122],"word-level":[106],"features.":[107,125],"second":[110],"categories":[119],"syllable-level":[124],"final":[128],"regression":[131],"predictor":[132],"trained":[134],"for":[140],"each":[141],"category.":[142],"conducted":[144],"both":[145],"subjective":[148,156],"tests":[149],"evaluate":[151],"proposed":[153,172],"method.":[154,173],"evaluation":[157],"showed":[158],"subjects":[160],"perceiving":[162],"noticeable":[164],"difference":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}