{"id":"https://openalex.org/W2778926431","doi":"https://doi.org/10.1109/icassp.2018.8461282","title":"On Using Backpropagation for Speech Texture Generation and Voice Conversion","display_name":"On Using Backpropagation for Speech Texture Generation and Voice Conversion","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2778926431","doi":"https://doi.org/10.1109/icassp.2018.8461282","mag":"2778926431"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.08363","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000408865","display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["Google Brain","[Google Brain]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google Brain","[Google Brain]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026650852","display_name":"Rif A. Saurous","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rif A. Saurous","raw_affiliation_strings":["Google Brain","[Google Brain]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samy Bengio","raw_affiliation_strings":["Google Brain","[Google Brain]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2256","last_page":"2260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9965999722480774,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7796757221221924},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.7171267867088318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6954253315925598},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.542472779750824},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5233451724052429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48729217052459717},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4674585461616516},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.439682275056839},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.435777485370636},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.29044559597969055},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1535699963569641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796757221221924},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.7171267867088318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6954253315925598},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.542472779750824},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5233451724052429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48729217052459717},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4674585461616516},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.439682275056839},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.435777485370636},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.29044559597969055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1535699963569641},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.08363","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.08363","pdf_url":"https://arxiv.org/pdf/1712.08363","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":"mag:2778926431","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1712.08363v2","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.1712.08363","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.08363","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.08363","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.08363","pdf_url":"https://arxiv.org/pdf/1712.08363","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2778926431.pdf","grobid_xml":"https://content.openalex.org/works/W2778926431.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W54257720","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1924619199","https://openalex.org/W2005126631","https://openalex.org/W2049686551","https://openalex.org/W2062663442","https://openalex.org/W2102113734","https://openalex.org/W2120847449","https://openalex.org/W2125027853","https://openalex.org/W2127006916","https://openalex.org/W2127141656","https://openalex.org/W2139788486","https://openalex.org/W2161208721","https://openalex.org/W2173520492","https://openalex.org/W2271840356","https://openalex.org/W2295130376","https://openalex.org/W2331128040","https://openalex.org/W2398826216","https://openalex.org/W2429018336","https://openalex.org/W2473388484","https://openalex.org/W2516608830","https://openalex.org/W2525778437","https://openalex.org/W2526050071","https://openalex.org/W2602489101","https://openalex.org/W2604184139","https://openalex.org/W2725868244","https://openalex.org/W2949382160","https://openalex.org/W2949888546","https://openalex.org/W2953022181","https://openalex.org/W2953054324","https://openalex.org/W2962851944","https://openalex.org/W2963207607","https://openalex.org/W2963403664","https://openalex.org/W2963609956","https://openalex.org/W2963702081","https://openalex.org/W2964301388","https://openalex.org/W2964308564","https://openalex.org/W4246354968","https://openalex.org/W6602211262","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6679436768","https://openalex.org/W6683590716","https://openalex.org/W6684191040","https://openalex.org/W6697028695","https://openalex.org/W6702130928","https://openalex.org/W6712560600","https://openalex.org/W6717740044","https://openalex.org/W6729110096","https://openalex.org/W6735369481"],"related_works":["https://openalex.org/W2963804033","https://openalex.org/W1585045112","https://openalex.org/W2891609809","https://openalex.org/W2945616452","https://openalex.org/W2900956255","https://openalex.org/W1964143424","https://openalex.org/W2168249605","https://openalex.org/W2163348148","https://openalex.org/W2119341451","https://openalex.org/W2253647218","https://openalex.org/W2736218237","https://openalex.org/W1505251852","https://openalex.org/W1545867029","https://openalex.org/W2941134668","https://openalex.org/W2770454110","https://openalex.org/W2962124356","https://openalex.org/W1604596145","https://openalex.org/W3109018774","https://openalex.org/W2240226698","https://openalex.org/W3081695446"],"abstract_inverted_index":{"Inspired":[0],"by":[1,39,70],"recent":[2],"work":[3],"on":[4,11,30,46],"neural":[5,43,64],"network":[6,15],"image":[7,60],"generation":[8],"which":[9],"rely":[10],"backpropagation":[12],"towards":[13],"the":[14,36,67,78],"inputs,":[16],"we":[17,85],"present":[18],"a":[19,40,72,87,95,120,137],"proof-of-concept":[20],"system":[21,68,102],"for":[22],"speech":[23,41,98,130],"texture":[24,61],"synthesis":[25,62],"and":[26,45,55,63,93,123],"voice":[27],"conversion":[28],"based":[29],"two":[31],"mechanisms:":[32],"approximate":[33],"inversion":[34],"of":[35,49,113],"representation":[37],"learned":[38],"recognition":[42,99],"network,":[44],"matching":[47],"statistics":[48],"neuron":[50],"activations":[51],"between":[52],"different":[53,138],"source":[54],"target":[56,114],"utterances.":[57],"Similar":[58],"to":[59,77,105,127],"style":[65],"transfer,":[66],"works":[69],"optimizing":[71],"cost":[73],"function":[74],"with":[75],"respect":[76],"input":[79],"waveform":[80],"samples.":[81],"To":[82],"this":[83],"end":[84],"use":[86],"differentiable":[88],"mel-filterbank":[89],"feature":[90],"extraction":[91],"pipeline":[92],"train":[94],"convolutional":[96],"cTC":[97],"network.":[100],"Our":[101],"is":[103],"able":[104],"extract":[106],"speaker":[107,115],"characteristics":[108],"from":[109],"very":[110],"limited":[111],"amounts":[112],"data,":[116],"as":[117,119],"little":[118],"few":[121],"seconds,":[122],"can":[124],"be":[125],"used":[126],"generate":[128],"realistic":[129],"babble":[131],"or":[132],"reconstruct":[133],"an":[134],"utterance":[135],"in":[136],"voice.":[139]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}