{"id":"https://openalex.org/W2890287821","doi":"https://doi.org/10.1109/icassp.2018.8461748","title":"Emphatic Speech Generation with Conditioned Input Layer and Bidirectional LSTMS for Expressive Speech Synthesis","display_name":"Emphatic Speech Generation with Conditioned Input Layer and Bidirectional LSTMS for Expressive Speech Synthesis","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890287821","doi":"https://doi.org/10.1109/icassp.2018.8461748","mag":"2890287821"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5102903512","display_name":"Runnan Li","orcid":"https://orcid.org/0000-0002-0922-003X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runnan Li","raw_affiliation_strings":["Dept. of Computer science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Dept. of Computer science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101530382","display_name":"Yuchen Huang","orcid":"https://orcid.org/0009-0008-9871-5851"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Huang","raw_affiliation_strings":["Dept. of Computer science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["MJRC, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"MJRC, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["MJRC, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"MJRC, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053661520","display_name":"Lianhong Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianhong Cai","raw_affiliation_strings":["Dept. of Computer science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":10,"citation_normalized_percentile":{"value":0.739672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":85,"max":86},"biblio":{"volume":null,"issue":null,"first_page":"5129","last_page":"5133"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9974,"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/T10028","display_name":"Topic Modeling","score":0.9949,"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/utterance","display_name":"Utterance","score":0.6626078},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.51668406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6949203},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6726138},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.67245394},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6626078},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.52859974},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.51668406},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47906718},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.45961234},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42391515},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.42293704},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41324407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41265938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3366477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26005095},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12427819},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.68,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1570874634","https://openalex.org/W2008406816","https://openalex.org/W2045158511","https://openalex.org/W2048389584","https://openalex.org/W2064675550","https://openalex.org/W2093265061","https://openalex.org/W2093820993","https://openalex.org/W2115210775","https://openalex.org/W2124388456","https://openalex.org/W2129142580","https://openalex.org/W2131774270","https://openalex.org/W2134973740","https://openalex.org/W2150355110","https://openalex.org/W2152175008","https://openalex.org/W2365209858","https://openalex.org/W2370788932","https://openalex.org/W2400063444","https://openalex.org/W2401700297","https://openalex.org/W2604735539","https://openalex.org/W2605320104","https://openalex.org/W2962965405","https://openalex.org/W46659105"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W40885451","https://openalex.org/W2946856121","https://openalex.org/W2535215250","https://openalex.org/W2433276473","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W1914543332","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"By":[0],"highlighting":[1],"the":[2,32,133],"focus":[3],"of":[4,46,52],"an":[5,15,148],"utterance":[6],"to":[7,120],"draw":[8],"attention,":[9],"emphasis":[10],"in":[11,31,88],"speech":[12,26,38,48,78,123,139,152],"interaction":[13],"plays":[14],"important":[16],"role":[17],"for":[18,58,106],"speaker":[19],"intention":[20],"expressing":[21],"and":[22,66,86,115,129,144],"understanding.":[23],"Therefore,":[24],"emphatic":[25,37,47,122,138,151],"synthesis":[27,79],"draws":[28],"increasing":[29],"interest":[30],"text-to-speech":[33],"(TTS)":[34],"area.":[35],"For":[36],"synthesis,":[39],"three":[40],"problems":[41],"still":[42],"exist:":[43],"1)":[44],"sparseness":[45],"data;":[49],"2)":[50],"flexibility":[51],"trained":[53],"model;":[54],"3)":[55],"modelling":[56,90],"shortage":[57],"secondary":[59],"emphasis.":[60],"Recently,":[61],"recurrent":[62],"neural":[63],"networks":[64],"(RNNs)":[65],"their":[67,84],"bidirectional":[68],"long":[69],"short":[70],"term":[71],"memory":[72],"(BLSTM)":[73],"variants":[74],"based":[75,109],"statistical":[76],"parametric":[77],"(SPSS)":[80],"systems":[81],"have":[82],"shown":[83],"adaptability":[85],"controllability":[87],"acoustic":[89],"thus":[91],"can":[92,136],"solve":[93],"aforementioned":[94],"problems.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99],"propose":[100],"a":[101],"novel":[102],"conditional":[103],"input":[104,119],"layer":[105],"conventional":[107],"BLSTM-RNN":[108],"approach":[110,135],"combining":[111],"using":[112],"emphasis-specific":[113],"vectors":[114],"linguistic":[116],"features":[117],"as":[118],"produce":[121,137],"trajectories.":[124],"Experimental":[125],"results":[126],"from":[127],"objective":[128],"subjective":[130],"evaluations":[131],"demonstrate":[132],"proposed":[134],"trajectories":[140],"with":[141],"high":[142],"quality":[143],"naturalness":[145],"only":[146],"requiring":[147],"additional":[149],"small-scale":[150],"corpus.":[153]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2890287821","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2024-12-30T12:50:06.265056","created_date":"2018-09-27"}