{"id":"https://openalex.org/W2974194285","doi":"https://doi.org/10.21437/ssw.2019-49","title":"Sequence to Sequence Neural Speech Synthesis with Prosody Modification Capabilities","display_name":"Sequence to Sequence Neural Speech Synthesis with Prosody Modification Capabilities","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2974194285","doi":"https://doi.org/10.21437/ssw.2019-49","mag":"2974194285"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-49","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.10302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Slava Shechtman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Alex Sorin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Sorin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5913,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87953696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"280"},"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":0.9968000054359436,"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":0.9958999752998352,"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":0.8472999930381775},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.510200023651123},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49900001287460327},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4526999890804291},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.43299999833106995},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4219000041484833}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8472999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984000205993652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6841999888420105},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2019-49","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.10302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.10302","pdf_url":"https://arxiv.org/pdf/1909.10302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.10302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.10302","pdf_url":"https://arxiv.org/pdf/1909.10302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"sequence":[1,3,22],"to":[2,9,23],"neural":[4,31],"TTS":[5],"systems":[6,14],"provide":[7],"close":[8],"natural":[10],"speech":[11,35,57],"quality.":[12],"Such":[13],"usually":[15],"comprise":[16],"a":[17,30,129,150,186],"network":[18],"converting":[19],"linguistic/phonetic":[20],"features":[21,26],"an":[24,75],"acoustic":[25,48],"sequence,":[27],"cascaded":[28],"with":[29,52],"vocoder.":[32],"The":[33,71],"generated":[34],"prosody":[36,61,72,140,163],"(i.e.":[37],"phoneme":[38],"durations,":[39],"pitch":[40],"and":[41,66,101,114,141,146,171,197],"loudness)":[42],"is":[43,63,84,106],"implicitly":[44],"present":[45,85],"in":[46,86,96,158],"the":[47,56,87,110,117,122,135,139,161,168,174],"features,":[49],"being":[50,154],"mixed":[51],"spectral":[53],"information.":[54],"Although":[55],"sounds":[58],"natural,":[59],"its":[60],"realization":[62],"randomly":[64],"chosen":[65],"cannot":[67],"be":[68],"easily":[69],"altered.":[70],"control":[73,148,164,195],"becomes":[74],"even":[76],"more":[77],"difficult":[78],"task":[79],"if":[80],"no":[81],"prosodic":[82],"labeling":[83],"training":[88,111],"data.":[89],"Recently,":[90],"much":[91],"progress":[92],"has":[93],"been":[94],"achieved":[95],"unsupervised":[97],"speaking":[98,118,144],"style":[99],"learning":[100],"generation,":[102],"however":[103],"human":[104],"inspection":[105],"still":[107],"required":[108],"after":[109],"for":[112],"discovery":[113],"interpretation":[115],"of":[116,138,173],"styles":[119],"learned":[120],"by":[121,156,179],"system.":[123],"In":[124],"this":[125],"work":[126],"we":[127],"introduce":[128],"fully":[130],"automatic":[131],"method":[132],"that":[133,191],"makes":[134],"system":[136],"aware":[137],"enables":[142],"sentence-wise":[143],"pace":[145,194],"expressiveness":[147,172],"on":[149],"continuous":[151],"scale.":[152],"While":[153],"useful":[155],"itself":[157],"many":[159],"applications,":[160],"proposed":[162],"can":[165],"also":[166,184],"improve":[167],"overall":[169],"quality":[170],"synthesized":[175],"speech,":[176],"as":[177],"demonstrated":[178],"subjective":[180],"listening":[181],"evaluations.":[182],"We":[183],"propose":[185],"novel":[187],"augmented":[188],"attention":[189,199],"mechanism,":[190],"facilitates":[192],"better":[193],"sensitivity":[196],"faster":[198],"convergence.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-09-26T00:00:00"}
