{"id":"https://openalex.org/W2605762339","doi":"https://doi.org/10.21437/interspeech.2017-349","title":"Learning Latent Representations for Speech Generation and Transformation","display_name":"Learning Latent Representations for Speech Generation and Transformation","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2605762339","doi":"https://doi.org/10.21437/interspeech.2017-349","mag":"2605762339"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-349","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/1704.04222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433382","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-6183-0612"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051950818"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":8.1907,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97954019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1273","last_page":"1277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.746832549571991},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6991844177246094},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6348683834075928},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6158942580223083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761566162109375},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5576481819152832},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5434094667434692},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49489229917526245},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.46800509095191956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4638407826423645},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4567514657974243},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4253509044647217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746832549571991},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6991844177246094},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6348683834075928},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6158942580223083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761566162109375},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5576481819152832},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5434094667434692},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49489229917526245},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.46800509095191956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4638407826423645},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4567514657974243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4253509044647217},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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:10.21437/interspeech.2017-349","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.04222","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.04222","pdf_url":"https://arxiv.org/pdf/1704.04222","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":"","raw_type":null},{"id":"mag:2605762339","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.04222.pdf","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.1704.04222","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.04222","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1704.04222","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.04222","pdf_url":"https://arxiv.org/pdf/1704.04222","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":"","raw_type":null},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2605762339.pdf","grobid_xml":"https://content.openalex.org/works/W2605762339.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1588266896","https://openalex.org/W1813508333","https://openalex.org/W1972420736","https://openalex.org/W1979651826","https://openalex.org/W2045956438","https://openalex.org/W2099621636","https://openalex.org/W2118154032","https://openalex.org/W2173520492","https://openalex.org/W2202109488","https://openalex.org/W2475998840","https://openalex.org/W2515020857","https://openalex.org/W2580178245","https://openalex.org/W2586950923","https://openalex.org/W2949382160","https://openalex.org/W2951004968","https://openalex.org/W2951298482","https://openalex.org/W2953331651"],"related_works":["https://openalex.org/W2962850167","https://openalex.org/W2099471712","https://openalex.org/W2964121744","https://openalex.org/W1959608418","https://openalex.org/W2963618559","https://openalex.org/W2753738274","https://openalex.org/W2515020857","https://openalex.org/W2949382160","https://openalex.org/W2532494225","https://openalex.org/W2608338293","https://openalex.org/W2467604901","https://openalex.org/W2187089797","https://openalex.org/W2064675550","https://openalex.org/W1663973292","https://openalex.org/W1524333225","https://openalex.org/W2527729766","https://openalex.org/W2157331557","https://openalex.org/W2120605154","https://openalex.org/W1909320841","https://openalex.org/W1552314771"],"abstract_inverted_index":{"An":[0],"ability":[1],"to":[2,21,55,69,81],"model":[3,56,80],"a":[4,9,52],"generative":[5,32,58],"process":[6,22,59],"and":[7],"learn":[8],"latent":[10,65,72],"representation":[11],"for":[12,90,100],"speech":[13,27,91],"in":[14,43],"an":[15],"unsupervised":[16],"fashion":[17],"will":[18],"be":[19],"crucial":[20],"vast":[23],"quantities":[24],"of":[25,60,78],"unlabelled":[26],"data.":[28,103],"Recently,":[29],"deep":[30],"probabilistic":[31],"models":[33],"such":[34],"as":[35],"Variational":[36],"Autoencoders":[37],"(VAEs)":[38],"have":[39],"achieved":[40],"tremendous":[41],"success":[42],"modeling":[44],"natural":[45,61],"images.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"apply":[51],"convolutional":[53],"VAE":[54],"the":[57,76,83,87,94,98],"speech.":[62],"We":[63,74],"derive":[64],"space":[66],"arithmetic":[67],"operations":[68],"disentangle":[70],"learned":[71],"representations.":[73],"demonstrate":[75],"capability":[77],"our":[79],"modify":[82],"phonetic":[84],"content":[85],"or":[86],"speaker":[88],"identity":[89],"segments":[92],"using":[93],"derived":[95],"operations,":[96],"without":[97],"need":[99],"parallel":[101],"supervisory":[102]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":2}],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-10-10T00:00:00"}