{"id":"https://openalex.org/W4290709727","doi":"https://doi.org/10.48550/arxiv.2110.15018","title":"TorchAudio: Building Blocks for Audio and Speech Processing","display_name":"TorchAudio: Building Blocks for Audio and Speech Processing","publication_year":2021,"publication_date":"2021-10-28","ids":{"openalex":"https://openalex.org/W4290709727","doi":"https://doi.org/10.48550/arxiv.2110.15018"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.15018","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15018","pdf_url":"https://arxiv.org/pdf/2110.15018","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.15018","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033186377","display_name":"Yao-Yuan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Yao-Yuan","raw_affiliation_strings":["University of California , San Diego ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego ,","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983396","display_name":"Moto Hira","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hira, Moto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Zhaoheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059137198","display_name":"Anjali Chourdia","orcid":"https://orcid.org/0009-0005-4276-2227","observed_orcids":["https://orcid.org/0009-0005-4276-2227"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chourdia, Anjali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034863556","display_name":"Artyom Astafurov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Astafurov, Artyom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010792181","display_name":"Caroline Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Caroline","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeh, Ching-Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029859679","display_name":"Christian Puhrsch","orcid":"https://orcid.org/0009-0002-3925-967X","observed_orcids":["https://orcid.org/0009-0002-3925-967X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puhrsch, Christian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pollack, David","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pollack, David","raw_affiliation_strings":["Solvemate Gmbh ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Solvemate Gmbh ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048470138","display_name":"Dmitriy Genzel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Genzel, Dmitriy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063628940","display_name":"Donny Greenberg","orcid":"https://orcid.org/0000-0002-5394-1627","observed_orcids":["https://orcid.org/0000-0002-5394-1627"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Greenberg, Donny","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101173534","display_name":"Edward Z. Yang","orcid":"https://orcid.org/0009-0008-0621-7872","observed_orcids":["https://orcid.org/0009-0008-0621-7872"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Edward Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lian, Jason","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahadeokar, Jay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021004964","display_name":"Jeff Hwang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Jeff","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731279","display_name":"Ji Chen","orcid":"https://orcid.org/0009-0006-1199-9747","observed_orcids":["https://orcid.org/0009-0006-1199-9747"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030372252","display_name":"Peter Goldsborough","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726938","display_name":"Anduril Industries (United States)","ror":"https://ror.org/012874a19","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726938"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Goldsborough, Peter","raw_affiliation_strings":["Anduril Industries ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anduril Industries ,","institution_ids":["https://openalex.org/I4401726938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070097883","display_name":"Prabhat Roy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy, Prabhat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090407830","display_name":"Sean Narenthiran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Narenthiran, Sean","raw_affiliation_strings":["Grid AI Labs ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grid AI Labs ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631","observed_orcids":["https://orcid.org/0000-0002-5970-8631"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Watanabe, Shinji","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002078510","display_name":"Soumith Chintala","orcid":"https://orcid.org/0000-0003-2147-9850","observed_orcids":["https://orcid.org/0000-0003-2147-9850"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chintala, Soumith","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036528438","display_name":"Vincent Quenneville-B\u00e9lair","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quenneville-B\u00e9lair, Vincent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155","observed_orcids":["https://orcid.org/0000-0001-5297-4155"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yangyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.6089000105857849,"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":0.6089000105857849,"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":0.3285999894142151,"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":0.05420000106096268,"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/audio-signal-processing","display_name":"audio signal processing","score":0.9490000009536743},{"id":"https://openalex.org/keywords/speech-processing","display_name":"speech processing","score":1.0},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.5609999895095825},{"id":"https://openalex.org/keywords/performance-benchmarking","display_name":"performance benchmarking","score":0.6930000185966492},{"id":"https://openalex.org/keywords/pytorch","display_name":"PyTorch","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543060421943665},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.804166316986084},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6579858064651489},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5322779417037964},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4952327311038971},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.48645564913749695},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4800654351711273},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47090768814086914},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.4684588611125946},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44660407304763794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32886970043182373},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3054075539112091},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.24709942936897278},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.19543927907943726},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1885901689529419},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2110.15018","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15018","pdf_url":"https://arxiv.org/pdf/2110.15018","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2110.15018","doi":"https://doi.org/10.48550/arxiv.2110.15018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.15018","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.15018","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15018","pdf_url":"https://arxiv.org/pdf/2110.15018","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4290709727.pdf","grobid_xml":"https://content.openalex.org/works/W4290709727.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2036021480","https://openalex.org/W4214505573","https://openalex.org/W2132241624","https://openalex.org/W4311683883","https://openalex.org/W4212902261","https://openalex.org/W2546377002","https://openalex.org/W4221030787","https://openalex.org/W2790811106","https://openalex.org/W4285209474","https://openalex.org/W2789551765"],"abstract_inverted_index":{"This":[0],"document":[1],"describes":[2],"version":[3],"0.10":[4],"of":[5,22,31,78,90,97,104,120],"TorchAudio:":[6],"building":[7,42,45],"blocks":[8,46],"for":[9,35],"machine":[10,32],"learning":[11,33],"applications":[12,34],"in":[13],"the":[14,27,67,91,115],"audio":[15,106],"and":[16,29,37,54,66,95,107,110,123,127],"speech":[17,108],"processing":[18],"domain.":[19],"The":[20,44],"objective":[21],"TorchAudio":[23,56],"is":[24,70],"to":[25,49,130],"accelerate":[26],"development":[28],"deployment":[30],"researchers":[36],"engineers":[38],"by":[39],"providing":[40],"off-the-shelf":[41],"blocks.":[43],"are":[47,125],"designed":[48],"be":[50,58],"GPU-compatible,":[51],"automatically":[52],"differentiable,":[53],"production-ready.":[55],"can":[57],"easily":[59],"installed":[60],"from":[61],"Python":[62],"Package":[63],"Index":[64],"repository":[65],"source":[68],"code":[69],"publicly":[71,132],"available":[72,133],"under":[73],"a":[74],"BSD-2-Clause":[75],"License":[76],"(as":[77],"September":[79],"2021)":[80],"at":[81],"https://github.com/pytorch/audio.":[82],"In":[83],"this":[84],"document,":[85],"we":[86],"provide":[87],"an":[88],"overview":[89],"design":[92],"principles,":[93],"functionalities,":[94],"benchmarks":[96,116],"TorchAudio.":[98],"We":[99,112],"also":[100],"benchmark":[101],"our":[102,118],"implementation":[103],"several":[105],"operations":[109,122],"models.":[111],"verify":[113],"through":[114],"that":[117],"implementations":[119],"various":[121],"models":[124],"valid":[126],"perform":[128],"similarly":[129],"other":[131],"implementations.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
