{"id":"https://openalex.org/W2924594913","doi":"https://doi.org/10.21437/interspeech.2019-1426","title":"Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis Through Audio Analysis","display_name":"Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis Through Audio Analysis","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2924594913","doi":"https://doi.org/10.21437/interspeech.2019-1426","mag":"2924594913"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.11570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017732845","display_name":"No\u00e9 Tits","orcid":"https://orcid.org/0000-0002-1971-4412"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"No\u00e9 Tits","raw_affiliation_strings":["University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047300919","display_name":"Fengna Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengna Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074305407","display_name":"Kevin El Haddad","orcid":"https://orcid.org/0000-0003-1465-6273"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kevin El Haddad","raw_affiliation_strings":["University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033039998","display_name":"Vincent Pagel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Pagel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042439255","display_name":"Thierry Dutoit","orcid":"https://orcid.org/0000-0001-7024-2150"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thierry Dutoit","raw_affiliation_strings":["University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017732845"],"corresponding_institution_ids":["https://openalex.org/I130929987"],"apc_list":null,"apc_paid":null,"fwci":0.289,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64974522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4475","last_page":"4479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T11309","display_name":"Music 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/T12031","display_name":"Speech and dialogue systems","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7574151754379272},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.7237303256988525},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5763009786605835},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5180228352546692},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.51004558801651},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5034272074699402},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45947542786598206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4476986825466156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3821036219596863},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3767874836921692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574151754379272},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.7237303256988525},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5763009786605835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5180228352546692},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.51004558801651},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5034272074699402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45947542786598206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4476986825466156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3821036219596863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3767874836921692},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-1426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.11570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.11570","pdf_url":"https://arxiv.org/pdf/1903.11570","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"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/42243","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/42243","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/42243/1/1426.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference of the International Speech Communication Association, Graz, Austria [AT], 2019","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2924594913","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1903.11570","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.11570","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.11570","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.11570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.11570","pdf_url":"https://arxiv.org/pdf/1903.11570","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2924594913.pdf","grobid_xml":"https://content.openalex.org/works/W2924594913.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1966797434","https://openalex.org/W1984314602","https://openalex.org/W2030931454","https://openalex.org/W2101234009","https://openalex.org/W2120847449","https://openalex.org/W2146334809","https://openalex.org/W2149628368","https://openalex.org/W2239141610","https://openalex.org/W2342475039","https://openalex.org/W2767052532","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2803193013","https://openalex.org/W2810914326","https://openalex.org/W2884607399","https://openalex.org/W2962691331","https://openalex.org/W2962788625","https://openalex.org/W2963182768","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2969658393"],"related_works":["https://openalex.org/W2979790850","https://openalex.org/W2976159681","https://openalex.org/W2610448050","https://openalex.org/W2546373232","https://openalex.org/W2612648756","https://openalex.org/W2056415906","https://openalex.org/W63300986","https://openalex.org/W2901611695","https://openalex.org/W1588565267","https://openalex.org/W16190262","https://openalex.org/W2335474826","https://openalex.org/W33124365","https://openalex.org/W1584278479","https://openalex.org/W176245312","https://openalex.org/W2258901759","https://openalex.org/W2141204697","https://openalex.org/W20372203","https://openalex.org/W2740883964","https://openalex.org/W1838628832","https://openalex.org/W2004934392"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,29,64,86],"Text-to-Speech":[3],"has":[4,41],"experienced":[5],"huge":[6],"improvements":[7],"last":[8],"years":[9],"benefiting":[10],"from":[11],"deep":[12],"learning":[13],"techniques.":[14],"Producing":[15],"realistic":[16],"speech":[17,35,100],"becomes":[18],"possible":[19],"now.":[20],"As":[21],"a":[22],"consequence,":[23],"the":[24,27,30,59,95],"research":[25],"on":[26,89],"control":[28,49,60],"expressiveness,":[31],"allowing":[32],"to":[33,48,70,97],"generate":[34],"in":[36],"different":[37,79],"styles":[38],"or":[39],"manners,":[40],"attracted":[42],"increasing":[43],"attention":[44],"lately.":[45],"Systems":[46],"able":[47],"style":[50],"have":[51],"been":[52],"developed":[53],"and":[54,67,77,82],"show":[55],"impressive":[56],"results.":[57],"However":[58],"parameters":[61],"often":[62],"consist":[63],"latent":[65,80],"variables":[66],"remain":[68],"complex":[69],"interpret.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"analyze":[76],"compare":[78],"spaces":[81],"obtain":[83],"an":[84,104],"interpretation":[85],"their":[87],"influence":[88],"expressive":[90],"speech.":[91],"This":[92],"will":[93],"enable":[94],"possibility":[96],"build":[98],"controllable":[99],"synthesis":[101],"systems":[102],"with":[103],"understandable":[105],"behaviour.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}