{"id":"https://openalex.org/W2795935131","doi":"https://doi.org/10.21437/interspeech.2018-38","title":"Conditional End-to-End Audio Transforms","display_name":"Conditional End-to-End Audio Transforms","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2795935131","doi":"https://doi.org/10.21437/interspeech.2018-38","mag":"2795935131"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/1804.00047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018264012","display_name":"Albert Haque","orcid":"https://orcid.org/0000-0001-6769-6370"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Albert Haque","raw_affiliation_strings":["Stanford University, Stanford, United States"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045861403","display_name":"Michelle Guo","orcid":"https://orcid.org/0000-0002-6574-6669"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Guo","raw_affiliation_strings":["Stanford University, Stanford, United States"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017296738","display_name":"Prateek Verma","orcid":"https://orcid.org/0000-0002-6402-8948"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prateek Verma","raw_affiliation_strings":["Stanford University, Stanford, United States"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018264012"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.4875,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90157403,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2295","last_page":"2299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.7418484687805176},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7102012038230896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6634526252746582},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5302947163581848},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43720555305480957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3065025508403778},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2242949903011322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418484687805176},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7102012038230896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6634526252746582},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5302947163581848},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43720555305480957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3065025508403778},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2242949903011322},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.00047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00047","pdf_url":"https://arxiv.org/pdf/1804.00047","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":"text"},{"id":"mag:2795935131","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1804.00047","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.1804.00047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.00047","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:1804.00047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00047","pdf_url":"https://arxiv.org/pdf/1804.00047","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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795935131.pdf","grobid_xml":"https://content.openalex.org/works/W2795935131.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1581808154","https://openalex.org/W1594494252","https://openalex.org/W1635512741","https://openalex.org/W1902237438","https://openalex.org/W2013996527","https://openalex.org/W2057609679","https://openalex.org/W2060895888","https://openalex.org/W2101346879","https://openalex.org/W2102988002","https://openalex.org/W2118090838","https://openalex.org/W2120605154","https://openalex.org/W2161208721","https://openalex.org/W2168274102","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2327501763","https://openalex.org/W2515943672","https://openalex.org/W2591927543","https://openalex.org/W2593116425","https://openalex.org/W2651834199","https://openalex.org/W2747744257","https://openalex.org/W2794490148","https://openalex.org/W2803963372","https://openalex.org/W2949888546","https://openalex.org/W2950577311","https://openalex.org/W2951535099","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2963804033","https://openalex.org/W2963840672","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2964352131"],"related_works":["https://openalex.org/W2963011080","https://openalex.org/W2782490852","https://openalex.org/W2916113431","https://openalex.org/W2963799213","https://openalex.org/W2936975153","https://openalex.org/W2593116425","https://openalex.org/W2516301810","https://openalex.org/W1522301498","https://openalex.org/W2740284003","https://openalex.org/W3107909154","https://openalex.org/W3046954891","https://openalex.org/W3033913438","https://openalex.org/W2963830550","https://openalex.org/W2790216641","https://openalex.org/W3034420534","https://openalex.org/W2594927458","https://openalex.org/W1558086160","https://openalex.org/W3157840621","https://openalex.org/W2972382840","https://openalex.org/W2798949062"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"end-to-end":[3],"method":[4,57,108],"for":[5],"transforming":[6],"audio":[7,85],"from":[8,99],"one":[9],"style":[10],"to":[11,29,74],"another.":[12],"For":[13,40],"the":[14,41,52],"case":[15,42],"of":[16,43],"speech,":[17],"by":[18,33],"conditioning":[19],"on":[20,64,112],"speaker":[21,95],"identities,":[22],"we":[23,45],"can":[24,46,93],"train":[25],"a":[26,59],"single":[27],"model":[28,62,92],"transform":[30],"words":[31],"spoken":[32],"multiple":[34,37],"people":[35],"into":[36],"target":[38],"voices.":[39],"music,":[44],"specify":[47],"musical":[48],"instruments":[49],"and":[50,66,82,96],"achieve":[51],"same":[53],"result.":[54],"Architecturally,":[55],"our":[56,91,107],"is":[58,72],"fully-differentiable":[60],"sequence-to-sequence":[61],"based":[63],"convolutional":[65],"hierarchical":[67],"recurrent":[68],"neural":[69],"networks.":[70],"It":[71],"designed":[73],"capture":[75],"long-term":[76],"acoustic":[77,100],"dependencies,":[78],"requires":[79],"minimal":[80],"post-processing,":[81],"produces":[83],"realistic":[84],"transforms.":[86],"Ablation":[87],"studies":[88],"confirm":[89],"that":[90],"separate":[94],"instrument":[97],"properties":[98],"content":[101],"at":[102],"different":[103],"receptive":[104],"fields.":[105],"Empirically,":[106],"achieves":[109],"competitive":[110],"performance":[111],"community-standard":[113],"datasets.":[114]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}