{"id":"https://openalex.org/W2901025079","doi":"https://doi.org/10.1109/icassp.2019.8682880","title":"Representation Mixing for TTS Synthesis","display_name":"Representation Mixing for TTS Synthesis","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2901025079","doi":"https://doi.org/10.1109/icassp.2019.8682880","mag":"2901025079"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1811.07240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037751863","display_name":"Kyle Kastner","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Kyle Kastner","raw_affiliation_strings":["MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]"],"affiliations":[{"raw_affiliation_string":"MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068457267","display_name":"Jo\u00e3o Felipe Santos","orcid":"https://orcid.org/0000-0003-3934-3943"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joao Felipe Santos","raw_affiliation_strings":["MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]"],"affiliations":[{"raw_affiliation_string":"MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]"],"affiliations":[{"raw_affiliation_string":"MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112608251","display_name":"Aaron Courville","orcid":"https://orcid.org/0000-0001-6223-0301"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aaron Courville","raw_affiliation_strings":["MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]"],"affiliations":[{"raw_affiliation_string":"MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"[MILA Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037751863"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":0.15361775,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5328961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"15","issue":null,"first_page":"5906","last_page":"5910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9943000078201294,"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":0.9916999936103821,"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":0.7346905469894409},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7227771878242493},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6209613084793091},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.6085801720619202},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5946572422981262},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5919243693351746},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5547029972076416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5360598564147949},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5336238741874695},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5262476801872253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4672994911670685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4451693594455719},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42881494760513306},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4131730794906616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30844488739967346},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12415418028831482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346905469894409},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7227771878242493},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6209613084793091},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6085801720619202},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5946572422981262},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5919243693351746},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5547029972076416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5360598564147949},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5336238741874695},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5262476801872253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4672994911670685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4451693594455719},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42881494760513306},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4131730794906616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30844488739967346},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12415418028831482},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.07240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.07240","pdf_url":"https://arxiv.org/pdf/1811.07240","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2901025079","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1811.07240","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.1811.07240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.07240","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.07240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.07240","pdf_url":"https://arxiv.org/pdf/1811.07240","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2901025079.pdf","grobid_xml":"https://content.openalex.org/works/W2901025079.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1593247906","https://openalex.org/W1989705633","https://openalex.org/W2064675550","https://openalex.org/W2120847449","https://openalex.org/W2131774270","https://openalex.org/W2150658333","https://openalex.org/W2159271068","https://openalex.org/W2194775991","https://openalex.org/W2475287302","https://openalex.org/W2767052532","https://openalex.org/W2795109282","https://openalex.org/W6638273328","https://openalex.org/W6638280674","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6679434410","https://openalex.org/W6695477072","https://openalex.org/W6697814554","https://openalex.org/W6732429163","https://openalex.org/W6736356763","https://openalex.org/W6736562241","https://openalex.org/W6741475896","https://openalex.org/W6746700228","https://openalex.org/W6749489859","https://openalex.org/W6753855596","https://openalex.org/W6756197946","https://openalex.org/W6802722711","https://openalex.org/W6864424756","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2963827314","https://openalex.org/W2964168688","https://openalex.org/W3026794213","https://openalex.org/W2053947571","https://openalex.org/W3096509182","https://openalex.org/W1553129813","https://openalex.org/W2939913319","https://openalex.org/W3025870691","https://openalex.org/W2894488315","https://openalex.org/W3010788072","https://openalex.org/W1968821173","https://openalex.org/W2611895873","https://openalex.org/W3089901025","https://openalex.org/W1877729219","https://openalex.org/W2251025892","https://openalex.org/W2172497561","https://openalex.org/W3132929045","https://openalex.org/W2228295943","https://openalex.org/W3190809486","https://openalex.org/W2763690830"],"abstract_inverted_index":{"Recent":[0],"character":[1,22],"and":[2,74],"phoneme-based":[3],"parametric":[4],"TTS":[5],"systems":[6],"using":[7],"deep":[8],"learning":[9],"have":[10],"shown":[11],"strong":[12],"performance":[13],"in":[14,40,55],"natural":[15],"speech":[16],"generation.":[17],"However,":[18],"the":[19,83],"choice":[20,64],"between":[21,65],"or":[23,68],"phoneme":[24],"input":[25],"can":[26],"create":[27],"serious":[28],"limitations":[29],"for":[30,48],"practical":[31],"deployment,":[32],"as":[33],"direct":[34],"control":[35],"of":[36,52,85],"pronunciation":[37],"is":[38],"crucial":[39],"certain":[41],"cases.":[42],"We":[43],"demonstrate":[44],"a":[45,56,78],"simple":[46],"method":[47],"combining":[49],"multiple":[50],"types":[51],"linguistic":[53],"information":[54],"single":[57],"encoder,":[58],"named":[59],"representation":[60],"mixing,":[61],"enabling":[62],"flexible":[63],"character,":[66],"phoneme,":[67],"mixed":[69],"representations":[70],"during":[71],"inference.":[72],"Experiments":[73],"user":[75],"studies":[76],"on":[77],"public":[79],"audiobook":[80],"corpus":[81],"show":[82],"efficacy":[84],"our":[86],"approach.":[87]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}