{"id":"https://openalex.org/W3130024583","doi":"https://doi.org/10.21437/interspeech.2021-1730","title":"Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion","display_name":"Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3130024583","doi":"https://doi.org/10.21437/interspeech.2021-1730","mag":"3130024583"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1730","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2102.11420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004564614","display_name":"Samuel J. Broughton","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Samuel J. Broughton","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085794127","display_name":"Asif Jalal","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Md. Asif Jalal","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033198799","display_name":"Roger K. Moore","orcid":"https://orcid.org/0000-0003-0065-3311"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roger K. Moore","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004564614"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02430216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"806","last_page":"810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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/interpretability","display_name":"Interpretability","score":0.9322991371154785},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7906129360198975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7467093467712402},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6466656923294067},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6138482093811035},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.599983274936676},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5558284521102905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49964237213134766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4687051475048065},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4249640107154846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39803850650787354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0945260226726532},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09266281127929688}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9322991371154785},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7906129360198975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467093467712402},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6466656923294067},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6138482093811035},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.599983274936676},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5558284521102905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49964237213134766},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4687051475048065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4249640107154846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39803850650787354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0945260226726532},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09266281127929688},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1730","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:180841","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:arXiv.org:2102.11420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.11420","pdf_url":"https://arxiv.org/pdf/2102.11420","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:3130024583","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.11420.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.2102.11420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.11420","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:2102.11420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.11420","pdf_url":"https://arxiv.org/pdf/2102.11420","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1588037970","https://openalex.org/W1903029394","https://openalex.org/W1915485278","https://openalex.org/W2013996527","https://openalex.org/W2017742648","https://openalex.org/W2022125261","https://openalex.org/W2025341678","https://openalex.org/W2057609679","https://openalex.org/W2086381917","https://openalex.org/W2099471712","https://openalex.org/W2100235303","https://openalex.org/W2120605154","https://openalex.org/W2123771434","https://openalex.org/W2126143605","https://openalex.org/W2156142001","https://openalex.org/W2194775991","https://openalex.org/W2471520273","https://openalex.org/W2473388484","https://openalex.org/W2502312327","https://openalex.org/W2527729766","https://openalex.org/W2553897675","https://openalex.org/W2576309025","https://openalex.org/W2593414223","https://openalex.org/W2603777577","https://openalex.org/W2608338293","https://openalex.org/W2666408839","https://openalex.org/W2746654391","https://openalex.org/W2747744257","https://openalex.org/W2749651610","https://openalex.org/W2767204723","https://openalex.org/W2787579267","https://openalex.org/W2796495654","https://openalex.org/W2891158090","https://openalex.org/W2949382160","https://openalex.org/W2952773607","https://openalex.org/W2953054324","https://openalex.org/W2962793481","https://openalex.org/W2963374347","https://openalex.org/W2963539064","https://openalex.org/W2963681776","https://openalex.org/W2963759780","https://openalex.org/W2963767194","https://openalex.org/W2963970792","https://openalex.org/W2965685620","https://openalex.org/W2972491522","https://openalex.org/W2995497846"],"related_works":["https://openalex.org/W3197531173","https://openalex.org/W3100696337","https://openalex.org/W2463547978","https://openalex.org/W2962813140","https://openalex.org/W3096048508","https://openalex.org/W2895358653","https://openalex.org/W2963463240","https://openalex.org/W115763757","https://openalex.org/W2175711684","https://openalex.org/W2946508582","https://openalex.org/W3200156078","https://openalex.org/W2898779401","https://openalex.org/W2890144771","https://openalex.org/W2919115771","https://openalex.org/W1951059531","https://openalex.org/W2798280084","https://openalex.org/W2803515177","https://openalex.org/W2896452596","https://openalex.org/W2291723583","https://openalex.org/W2937449824"],"abstract_inverted_index":{"Generative":[0],"Adversarial":[1],"Networks":[2],"(GANs)":[3],"are":[4],"machine":[5],"learning":[6,148,180],"networks":[7,177],"based":[8],"around":[9],"creating":[10],"synthetic":[11],"data.":[12,67],"Voice":[13],"Conversion":[14],"(VC)":[15],"is":[16,49,114,121],"a":[17,29,33,99,137],"subset":[18],"of":[19,28,43,65,77,80,86,98,117,127,136,157,174,187],"voice":[20],"translation":[21],"that":[22,90,112,120],"involves":[23],"translating":[24],"the":[25,38,63,69,75,84,91,95,115,125,128,133,160,171,182,185],"paralinguistic":[26],"features":[27],"source":[30],"speaker":[31,35],"to":[32,50,60,105],"target":[34],"while":[36],"preserving":[37],"linguistic":[39],"information.":[40],"The":[41],"aim":[42],"non-parallel":[44,81],"conditional":[45],"GANs":[46,82],"for":[47,124],"VC":[48],"translate":[51],"an":[52],"acoustic":[53],"speech":[54],"feature":[55],"sequence":[56],"from":[57],"one":[58,141],"domain":[59,85],"another":[61,150],"without":[62],"use":[64],"paired":[66],"In":[68],"study":[70],"reported":[71],"here,":[72],"we":[73],"investigated":[74],"interpretability":[76],"state-of-the-art":[78],"implementations":[79],"in":[83,94,184],"VC.":[87],"We":[88,130],"show":[89],"learned":[92,134,172],"representations":[93,135,173],"repeating":[96,118],"layers":[97,119],"particular":[100,142],"GAN":[101],"architecture":[102],"remain":[103],"close":[104],"their":[106],"original":[107],"random":[108],"initialised":[109],"parameters,":[110],"demonstrating":[111],"it":[113],"number":[116,186],"more":[122],"responsible":[123],"quality":[126],"output.":[129],"also":[131],"analysed":[132],"model":[138],"trained":[139],"on":[140,149],"dataset":[143],"when":[144],"used":[145],"during":[146,179],"transfer":[147],"dataset.":[151],"This":[152],"showed":[153],"extremely":[154],"high":[155],"levels":[156],"similarity":[158],"across":[159],"entire":[161],"network.":[162],"Together,":[163],"these":[164],"results":[165],"provide":[166],"new":[167],"insight":[168],"into":[169],"how":[170],"deep":[175],"generative":[176],"change":[178],"and":[181],"importance":[183],"layers.":[188]},"counts_by_year":[],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-25T00:00:00"}