{"id":"https://openalex.org/W2584032004","doi":"https://doi.org/10.48550/arxiv.1612.07837","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","display_name":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","publication_year":2016,"publication_date":"2016-12-22","ids":{"openalex":"https://openalex.org/W2584032004","doi":"https://doi.org/10.48550/arxiv.1612.07837","mag":"2584032004"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1612.07837","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.07837","pdf_url":"https://arxiv.org/pdf/1612.07837","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.07837","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083454446","display_name":"Soroush Mehri","orcid":null,"observed_orcids":[]},"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":"Mehri, Soroush","raw_affiliation_strings":["University of Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419280","display_name":"Kundan Kumar","orcid":"https://orcid.org/0000-0002-3784-4819","observed_orcids":["https://orcid.org/0000-0002-3784-4819","https://orcid.org/0009-0006-5131-3527"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kumar, Kundan","raw_affiliation_strings":["IIT Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025335469","display_name":"Ishaan Gulrajani","orcid":null,"observed_orcids":[]},"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":"Gulrajani, Ishaan","raw_affiliation_strings":["University of Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076833789","display_name":"Rithesh Kumar","orcid":"https://orcid.org/0009-0000-6881-2783","observed_orcids":["https://orcid.org/0009-0000-6881-2783"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kumar, Rithesh","raw_affiliation_strings":["IIT Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jain, Shubham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jain, Shubham","raw_affiliation_strings":["IIT Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064354030","display_name":"Jose Sotelo","orcid":null,"observed_orcids":[]},"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":"Sotelo, Jose","raw_affiliation_strings":["University of Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112608251","display_name":"Aaron C. Courville","orcid":"https://orcid.org/0000-0001-6223-0301","observed_orcids":["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":"Courville, Aaron","raw_affiliation_strings":["University of Montreal CIFAR Fellow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal CIFAR Fellow","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515","observed_orcids":["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":"Bengio, Yoshua","raw_affiliation_strings":["University of Montreal CIFAR Senior Fellow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal CIFAR Senior Fellow","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":558,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7139000296592712,"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":0.7139000296592712,"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":0.21240000426769257,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.06129999831318855,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.7768843770027161},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7615699768066406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406421303749084},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6671785712242126},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6250914931297302},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5617168545722961},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5386161208152771},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4613611102104187},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.44168925285339355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436382532119751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4029203951358795},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.12401032447814941},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11362981796264648},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1612.07837","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.07837","pdf_url":"https://arxiv.org/pdf/1612.07837","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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:2953331651","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1612.07837","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.1612.07837","doi":"https://doi.org/10.48550/arxiv.1612.07837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1612.07837","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1612.07837","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.07837","pdf_url":"https://arxiv.org/pdf/1612.07837","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320311777","display_name":"Secretar\u00eda de Educaci\u00f3n P\u00fablica","ror":"https://ror.org/02e1c4h55"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2584032004.pdf","grobid_xml":"https://content.openalex.org/works/W2584032004.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1810943226","https://openalex.org/W1924770834","https://openalex.org/W2053429109","https://openalex.org/W2053831280","https://openalex.org/W2064675550","https://openalex.org/W2107789863","https://openalex.org/W2135181320","https://openalex.org/W2184335310","https://openalex.org/W2267126114","https://openalex.org/W2273818272","https://openalex.org/W2286929393","https://openalex.org/W2519091744","https://openalex.org/W2581073931","https://openalex.org/W2962883855","https://openalex.org/W2963685250","https://openalex.org/W2964121744","https://openalex.org/W4394663752"],"related_works":["https://openalex.org/W2915977493","https://openalex.org/W4416368248","https://openalex.org/W2948211236","https://openalex.org/W4377010126","https://openalex.org/W7064045641","https://openalex.org/W2519091744","https://openalex.org/W7165678770","https://openalex.org/W4300980117","https://openalex.org/W3024973272","https://openalex.org/W4318902838"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"a":[5,19,42],"novel":[6],"model":[7,77,91],"for":[8],"unconditional":[9],"audio":[10,16],"generation":[11],"based":[12],"on":[13,62,70],"generating":[14],"one":[15],"sample":[17],"at":[18],"time.":[20],"We":[21,83],"show":[22,85],"that":[23,75],"our":[24,76],"model,":[25],"which":[26],"profits":[27],"from":[28],"combining":[29],"memory-less":[30],"modules,":[31],"namely":[32],"autoregressive":[33],"multilayer":[34],"perceptrons,":[35],"and":[36],"stateful":[37],"recurrent":[38],"neural":[39],"networks":[40],"in":[41,53],"hierarchical":[43],"structure":[44],"is":[45,78],"able":[46],"to":[47,93],"capture":[48],"underlying":[49],"sources":[50],"of":[51,65,89],"variations":[52],"the":[54,71,90,94],"temporal":[55],"sequences":[56],"over":[57,80],"very":[58],"long":[59],"time":[60],"spans,":[61],"three":[63],"datasets":[64],"different":[66],"nature.":[67],"Human":[68],"evaluation":[69],"generated":[72],"samples":[73],"indicate":[74],"preferred":[79],"competing":[81],"models.":[82],"also":[84],"how":[86],"each":[87],"component":[88],"contributes":[92],"exhibited":[95],"performance.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":50},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":85},{"year":2020,"cited_by_count":96},{"year":2019,"cited_by_count":90},{"year":2018,"cited_by_count":69},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2017-02-10T00:00:00"}
