{"id":"https://openalex.org/W2394662942","doi":"https://doi.org/10.21437/interspeech.2014-445","title":"Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks","display_name":"Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2394662942","doi":"https://doi.org/10.21437/interspeech.2014-445","mag":"2394662942"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raul Fernandez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049126763","display_name":"Asaf Rendel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asaf Rendel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2268","last_page":"2272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700463593006134},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6897463798522949},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.649876594543457},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.637270450592041},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.6113282442092896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.559306263923645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49871349334716797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48626554012298584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700463593006134},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6897463798522949},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.649876594543457},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.637270450592041},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.6113282442092896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.559306263923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49871349334716797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48626554012298584},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1514737389","https://openalex.org/W1522612817","https://openalex.org/W2020024436","https://openalex.org/W2045158511","https://openalex.org/W2064675550","https://openalex.org/W2076638338","https://openalex.org/W2094035326","https://openalex.org/W2102003408","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2143908786","https://openalex.org/W2154920538","https://openalex.org/W2160473997","https://openalex.org/W2170942820","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2566606998","https://openalex.org/W2406264770","https://openalex.org/W4366149782","https://openalex.org/W1897240248","https://openalex.org/W3103945224","https://openalex.org/W1583001605","https://openalex.org/W3015193452","https://openalex.org/W3038306631","https://openalex.org/W2755891984","https://openalex.org/W2394662942"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"been":[5],"shown":[6],"to":[7,56],"provide":[8,96],"state-of-the-art":[9],"performance":[10,98],"over":[11,99],"other":[12],"baseline":[13],"models":[14],"in":[15,24,75,104,123,135,141],"the":[16],"task":[17],"of":[18,37,68,101,106,113,120,132,143],"predicting":[19],"prosodic":[20,114],"targets":[21],"from":[22,82],"text":[23],"a":[25,44,50,65,90,111,117,129],"speechsynthesis":[26],"system.":[27],"However,":[28],"prosody":[29,155],"prediction":[30],"can":[31,54,78],"be":[32],"affected":[33],"by":[34,128],"an":[35,83],"interaction":[36],"short-":[38],"and":[39,77],"long-term":[40],"contextual":[41],"factors":[42],"that":[43,47,72,94],"static":[45],"model":[46],"depends":[48],"on":[49],"fixed-size":[51],"context":[52],"window":[53],"fail":[55],"properly":[57],"capture.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"look":[63],"at":[64],"recurrent":[66,157],"formulation":[67],"neural":[69,158],"networks":[70],"(RNNs)":[71],"are":[73],"deep":[74,160],"time":[76],"store":[79],"state":[80],"information":[81],"arbitrarily":[84],"large":[85],"input":[86],"history":[87],"when":[88],"making":[89],"prediction.":[91],"We":[92],"show":[93],"RNNs":[95],"improved":[97],"DNNs":[100],"comparable":[102],"size":[103],"terms":[105,142],"various":[107],"objective":[108],"metrics":[109],"for":[110],"variety":[112],"streams":[115],"(notably,":[116],"relative":[118,130],"reduction":[119],"about":[121,133],"6%":[122],"F0":[124,136],"mean-square":[125],"error":[126],"accompanied":[127],"increase":[131],"14%":[134],"variance),":[137],"as":[138,140],"well":[139],"perceptual":[144],"quality":[145],"assessed":[146],"through":[147],"mean-opinion-score":[148],"listening":[149],"tests.":[150],"Index":[151],"Terms:":[152],"speech":[153],"synthesis,text-to-speech,":[154],"prediction,":[156],"networks,":[159],"learning":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}