{"id":"https://openalex.org/W2953190524","doi":"https://doi.org/10.1109/icassp.2019.8683535","title":"Wav2Letter++: A Fast Open-source Speech Recognition System","display_name":"Wav2Letter++: A Fast Open-source Speech Recognition System","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2953190524","doi":"https://doi.org/10.1109/icassp.2019.8683535","mag":"2953190524"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.07625","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Vineel Pratap","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087325198","display_name":"Awni Hannun","orcid":"https://orcid.org/0000-0003-3080-4002"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Awni Hannun","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102647000","display_name":"Qiantong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049890825","display_name":"Jeff Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jeff Cai","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027275703","display_name":"Jacob Kahn","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Kahn","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025751434","display_name":"Vitaliy Liptchinsky","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Vitaliy Liptchinsky","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.2211,"has_fulltext":false,"cited_by_count":170,"citation_normalized_percentile":{"value":0.9937366,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6460","last_page":"6464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9944000244140625,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9939000010490417,"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":0.7953013777732849},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6796689033508301},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6384100914001465},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4831056594848633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4528263211250305},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.43028855323791504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297023117542267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33619165420532227},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.15639591217041016},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11034122109413147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953013777732849},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6796689033508301},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6384100914001465},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4831056594848633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4528263211250305},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.43028855323791504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297023117542267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33619165420532227},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.15639591217041016},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11034122109413147},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.07625","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07625","pdf_url":"https://arxiv.org/pdf/1812.07625","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.07625","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07625","pdf_url":"https://arxiv.org/pdf/1812.07625","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1667652561","https://openalex.org/W1922655562","https://openalex.org/W1988057723","https://openalex.org/W2024490156","https://openalex.org/W2102182691","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2134800885","https://openalex.org/W2402144811","https://openalex.org/W2404126548","https://openalex.org/W2514741789","https://openalex.org/W2520160253","https://openalex.org/W2781384251","https://openalex.org/W2795935804","https://openalex.org/W2804704270","https://openalex.org/W2899771611","https://openalex.org/W2901739041","https://openalex.org/W2953384591","https://openalex.org/W2962780374","https://openalex.org/W2963211739","https://openalex.org/W2964277995","https://openalex.org/W2964308564","https://openalex.org/W4297818305","https://openalex.org/W4302296459","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6637151318","https://openalex.org/W6640090968","https://openalex.org/W6679434410","https://openalex.org/W6679855610","https://openalex.org/W6713134421","https://openalex.org/W6727336983","https://openalex.org/W6747270024","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2124842464","https://openalex.org/W2382657549","https://openalex.org/W4376877853","https://openalex.org/W75565505","https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W3200723557","https://openalex.org/W4205824991","https://openalex.org/W4214847518","https://openalex.org/W4312713546"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"wav2letter++,":[3],"a":[4,98],"fast":[5,93],"open-source":[6,43],"deep":[7],"learning":[8],"speech":[9,44,66],"recognition":[10,45],"framework.":[11],"wav2letter++":[12,35,50,72],"is":[13,51,96],"written":[14],"entirely":[15],"in":[16,101],"C++,":[17],"and":[18,31,37,104,110],"uses":[19],"the":[20,29,34,80],"ArrayFire":[21],"tensor":[22],"library":[23],"for":[24,60,65,84],"maximum":[25],"efficiency.":[26],"We":[27,68],"explain":[28],"architecture":[30],"design":[32],"of":[33],"system":[36],"compare":[38],"it":[39],"to":[40,77],"other":[41,57],"major":[42],"systems.":[46],"In":[47],"some":[48],"cases":[49],"more":[52],"than":[53,56],"2\u00d7":[54],"faster":[55],"optimized":[58],"frameworks":[59,91],"training":[61,73],"end-to-end":[62],"neural":[63],"networks":[64],"recognition.":[67],"also":[69],"show":[70],"that":[71],"times":[74],"scale":[75],"linearly":[76],"64":[78],"GPUs,":[79],"most":[81],"we":[82],"tested,":[83],"models":[85],"with":[86],"100":[87],"million":[88],"parameters.":[89],"High-performance":[90],"enable":[92],"iteration,":[94],"which":[95],"often":[97],"crucial":[99],"factor":[100],"successful":[102],"research":[103],"model":[105],"tuning":[106],"on":[107],"new":[108],"datasets":[109],"tasks.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":44},{"year":2019,"cited_by_count":18}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2019-06-27T00:00:00"}