{"id":"https://openalex.org/W2890116704","doi":"https://doi.org/10.1109/icassp.2018.8462473","title":"Emphatic Speech Prosody Prediction with Deep Lstm Networks","display_name":"Emphatic Speech Prosody Prediction with Deep Lstm Networks","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890116704","doi":"https://doi.org/10.1109/icassp.2018.8462473","mag":"2890116704"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["IBM Research AI, Haifa Research Lab, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Haifa Research Lab, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013894504","display_name":"Moran Mordechay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Moran Mordechay","raw_affiliation_strings":["IBM Research AI, Haifa Research Lab, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Haifa Research Lab, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8448,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80623443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5119","last_page":"5123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.8160396814346313},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.7852219343185425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7841958999633789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6106833815574646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5906888246536255},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5714837908744812},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5316551327705383},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5206922292709351},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.4949004054069519},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.469819575548172},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4437887370586395},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.44265955686569214},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.43721893429756165},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4279749393463135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39243006706237793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07609531283378601}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8160396814346313},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.7852219343185425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841958999633789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6106833815574646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906888246536255},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5714837908744812},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5316551327705383},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5206922292709351},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4949004054069519},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.469819575548172},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4437887370586395},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.44265955686569214},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.43721893429756165},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4279749393463135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39243006706237793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07609531283378601},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W5866514","https://openalex.org/W2048389584","https://openalex.org/W2154280657","https://openalex.org/W2160473997","https://openalex.org/W2396931946","https://openalex.org/W2398699645","https://openalex.org/W2510638983","https://openalex.org/W2519091744","https://openalex.org/W2612157710","https://openalex.org/W2890116704","https://openalex.org/W2964301388","https://openalex.org/W6600265255","https://openalex.org/W6662592903","https://openalex.org/W6683480319","https://openalex.org/W6712324455","https://openalex.org/W6754443558"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W2396586136","https://openalex.org/W4391272374","https://openalex.org/W1505084104","https://openalex.org/W2599935372","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W10581632","https://openalex.org/W1927421023"],"abstract_inverted_index":{"Controllable":[0],"generation":[1,40],"of":[2,25,86,113],"emphasis":[3,26,52,56,77],"in":[4,13,103],"speech":[5],"is":[6],"desirable":[7],"for":[8,49],"expressive":[9],"TTS":[10,116],"systems":[11],"utilized":[12],"various":[14,87],"dialog":[15],"applications.":[16],"Usually":[17],"such":[18],"models":[19,108],"remain":[20],"voice-specific":[21],"and":[22,111],"the":[23,114],"strength":[24,78],"can't":[27],"be":[28],"readily":[29],"controlled.":[30],"In":[31],"this":[32],"work":[33],"we":[34,90],"present":[35],"a":[36,92,96],"flexible":[37],"emphatic":[38,83],"prosody":[39,84],"model":[41,58,94],"based":[42],"on":[43,61],"Deep":[44],"Recurrent":[45],"Neural":[46],"Networks":[47],"(DRNN)":[48],"controllable":[50],"word-level":[51],"realization.":[53],"The":[54],"word":[55],"DRNN":[57,93],"was":[59,73],"trained":[60,91],"syllable-level":[62],"piecewise":[63],"linear":[64],"prosodic":[65],"trajectory":[66],"parameters.":[67],"A":[68],"special":[69],"data":[70],"preprocessing":[71],"technique":[72],"introduced":[74],"to":[75,81],"enable":[76],"control,":[79],"allowing":[80],"generate":[82],"trajectories":[85],"strength.":[88],"Additionally,":[89],"generating":[95],"sentence-level":[97],"emphasis,":[98],"i.e.":[99],"producing":[100],"whole":[101],"sentences":[102],"forceful,":[104],"decisive":[105],"manner.":[106],"Both":[107],"preserve":[109],"quality":[110],"naturalness":[112],"baseline":[115],"output.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}