{"id":"https://openalex.org/W3125687907","doi":"https://doi.org/10.1109/slt48900.2021.9383591","title":"Supervised and unsupervised approaches for controlling narrow lexical focus in sequence-to-sequence speech synthesis","display_name":"Supervised and unsupervised approaches for controlling narrow lexical focus in sequence-to-sequence speech synthesis","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3125687907","doi":"https://doi.org/10.1109/slt48900.2021.9383591","mag":"3125687907"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.09940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"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 Haifa Research Lab, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Haifa Research Lab, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Raul Fernandez","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raul Fernandez","raw_affiliation_strings":["IBM TJ Watson Research Lab, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Lab, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":null,"display_name":"David Haws","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Haws","raw_affiliation_strings":["IBM TJ Watson Research Lab, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Lab, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8396,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77770404,"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":"431","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8302000164985657},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.645799994468689},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6450999975204468},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6327000260353088},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6035000085830688},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5759999752044678},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5475999712944031},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4731000065803528}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8302000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985000014305115},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.645799994468689},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6450999975204468},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt48900.2021.9383591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.09940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.09940","pdf_url":"https://arxiv.org/pdf/2101.09940","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:2101.09940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.09940","pdf_url":"https://arxiv.org/pdf/2101.09940","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1539337024","https://openalex.org/W2048389584","https://openalex.org/W2102146461","https://openalex.org/W2154280657","https://openalex.org/W2398699645","https://openalex.org/W2510638983","https://openalex.org/W2795109282","https://openalex.org/W2888855092","https://openalex.org/W2890116704","https://openalex.org/W2904459034","https://openalex.org/W2938102059","https://openalex.org/W2963091184","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W2974194285","https://openalex.org/W3007067948","https://openalex.org/W3008691130","https://openalex.org/W3015645837","https://openalex.org/W6631190155","https://openalex.org/W6712402296","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6763832098","https://openalex.org/W6773677069","https://openalex.org/W6778823374","https://openalex.org/W6780226713"],"related_works":[],"abstract_inverted_index":{"Although":[0],"Sequence-to-Sequence":[1],"(S2S)":[2],"architectures":[3,73],"have":[4],"become":[5],"state-of-the-art":[6],"in":[7,126],"speech":[8],"synthesis,":[9],"capable":[10,44],"of":[11,19,28,45,53,65,72,79,85],"generating":[12],"outputs":[13],"that":[14,95],"approach":[15],"the":[16,35,47,63,83,107,120],"perceptual":[17],"quality":[18],"natural":[20],"samples,":[21],"they":[22],"are":[23,98],"limited":[24],"by":[25],"a":[26,42,51,70,127],"lack":[27],"flexibility":[29],"when":[30,124],"it":[31],"comes":[32],"to":[33,62,75,100],"controlling":[34,46],"output.":[36],"In":[37],"this":[38,60],"work":[39],"we":[40,97,117],"present":[41],"framework":[43,61],"prosodic":[48],"output":[49],"via":[50,92],"set":[52],"concise,":[54],"interpretable,":[55],"disentangled":[56],"parameters.":[57],"We":[58,88],"apply":[59],"realization":[64],"emphatic":[66],"lexical":[67],"focus,":[68],"proposing":[69],"variety":[71],"designed":[74],"exploit":[76],"different":[77,121],"levels":[78],"supervision":[80],"based":[81],"on":[82],"availability":[84],"labeled":[86,133],"resources.":[87],"evaluate":[89],"these":[90],"approaches":[91,122],"listening":[93],"tests":[94],"demonstrate":[96],"able":[99],"successfully":[101],"realize":[102],"controllable":[103],"focus":[104],"while":[105],"maintaining":[106],"same,":[108],"or":[109,131],"higher,":[110],"naturalness":[111],"over":[112],"an":[113],"established":[114],"baseline,":[115],"and":[116],"explore":[118],"how":[119],"compare":[123],"synthesizing":[125],"target":[128],"voice":[129],"with":[130],"without":[132],"data.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-02-01T00:00:00"}