{"id":"https://openalex.org/W3208743843","doi":"https://doi.org/10.1109/icassp43922.2022.9747236","title":"Torchaudio: Building Blocks for Audio and Speech Processing","display_name":"Torchaudio: Building Blocks for Audio and Speech Processing","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3208743843","doi":"https://doi.org/10.1109/icassp43922.2022.9747236","mag":"3208743843"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747236","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033186377","display_name":"Yao-Yuan Yang","orcid":null},"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":true,"raw_author_name":"Yao-Yuan Yang","raw_affiliation_strings":["University of California,San Diego","University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]},{"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},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moto Hira","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034863556","display_name":"Artyom Astafurov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artyom Astafurov","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010792181","display_name":"Caroline Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caroline Chen","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029859679","display_name":"Christian Puhrsch","orcid":"https://orcid.org/0009-0002-3925-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Puhrsch","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081927244","display_name":"David Pollack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Pollack","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},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitriy Genzel","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063628940","display_name":"Donny Greenberg","orcid":"https://orcid.org/0000-0002-5394-1627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donny Greenberg","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101173534","display_name":"Edward Z. Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward Z. Yang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011029140","display_name":"Jason Lian","orcid":"https://orcid.org/0009-0001-8798-924X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Lian","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021004964","display_name":"Jeff Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Hwang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731268","display_name":"Ji Chen","orcid":"https://orcid.org/0000-0001-6944-2729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Chen","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030372252","display_name":"Peter Goldsborough","orcid":null},"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":"Peter Goldsborough","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/A5090407830","display_name":"Sean Narenthiran","orcid":null},"institutions":[{"id":"https://openalex.org/I172637570","display_name":"National Grid (United States)","ror":"https://ror.org/04vdxde73","country_code":"US","type":"company","lineage":["https://openalex.org/I172637570","https://openalex.org/I4210155979"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Narenthiran","raw_affiliation_strings":["Grid AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grid AI Labs","institution_ids":["https://openalex.org/I172637570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"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":"Shinji Watanabe","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"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soumith Chintala","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036528438","display_name":"Vincent Quenneville-B\u00e9lair","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Quenneville-Belair","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":18,"corresponding_author_ids":["https://openalex.org/A5033186377"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":11.8994,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.99055713,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6982","last_page":"6986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8739198446273804},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7936483025550842},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6399369239807129},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5189213752746582},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49292922019958496},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4873548448085785},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.48198074102401733},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.48173192143440247},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.45867520570755005},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44492438435554504},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4101223647594452},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.31855785846710205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2964777946472168},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2907540798187256},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.208449125289917},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1914721429347992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8739198446273804},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7936483025550842},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6399369239807129},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5189213752746582},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49292922019958496},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4873548448085785},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48198074102401733},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.48173192143440247},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.45867520570755005},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44492438435554504},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4101223647594452},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31855785846710205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2964777946472168},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2907540798187256},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.208449125289917},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1914721429347992},{"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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747236","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1922655562","https://openalex.org/W2191779130","https://openalex.org/W2520160253","https://openalex.org/W2933138175","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2963300588","https://openalex.org/W2964227577","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970971581","https://openalex.org/W2974231335","https://openalex.org/W2995233853","https://openalex.org/W2998572311","https://openalex.org/W3000389243","https://openalex.org/W3008912312","https://openalex.org/W3035965352","https://openalex.org/W3036601975","https://openalex.org/W3095717210","https://openalex.org/W3099330747","https://openalex.org/W3099782249","https://openalex.org/W3099878876","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W4287632494","https://openalex.org/W4295312788","https://openalex.org/W4298580827","https://openalex.org/W6640090968","https://openalex.org/W6727336983","https://openalex.org/W6748409065","https://openalex.org/W6766978945","https://openalex.org/W6767671539","https://openalex.org/W6771763809","https://openalex.org/W6772349387","https://openalex.org/W6780218876","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2036021480","https://openalex.org/W2132241624","https://openalex.org/W4311683883","https://openalex.org/W4212902261","https://openalex.org/W4400311305","https://openalex.org/W2790811106","https://openalex.org/W4385413248","https://openalex.org/W2546377002","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":2026,"cited_by_count":8},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":12}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}
