{"id":"https://openalex.org/W2973215447","doi":"https://doi.org/10.21437/interspeech.2019-1819","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","display_name":"Jasper: An End-to-End Convolutional Neural Acoustic Model","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973215447","doi":"https://doi.org/10.21437/interspeech.2019-1819","mag":"2973215447"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1819","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Li","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090541149","display_name":"R. Bret Leary","orcid":"https://orcid.org/0000-0003-3771-8465"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Leary","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048403564","display_name":"Oleksii Kuchaiev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleksii Kuchaiev","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079416691","display_name":"Jonathan Cohen","orcid":"https://orcid.org/0000-0003-1004-5598"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan M. Cohen","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564876","display_name":"Huyen Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huyen Nguyen","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050071432","display_name":"Ravi Teja Gadde","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Teja Gadde","raw_affiliation_strings":["New York University, New York, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100762970"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":20.2561,"has_fulltext":false,"cited_by_count":214,"citation_normalized_percentile":{"value":0.99471811,"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":"71","last_page":"75"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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/T11309","display_name":"Music and Audio Processing","score":0.9934999942779541,"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/dropout","display_name":"Dropout (neural networks)","score":0.7899124622344971},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.763276219367981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146716117858887},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6253654956817627},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5989084243774414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5749127268791199},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5651215314865112},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5412525534629822},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5127359628677368},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4988136291503906},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.4807957708835602},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.43770310282707214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37008023262023926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2345079779624939},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18181157112121582},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.13596197962760925},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0685042142868042}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7899124622344971},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.763276219367981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146716117858887},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6253654956817627},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5989084243774414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5749127268791199},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5651215314865112},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5412525534629822},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5127359628677368},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4988136291503906},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.4807957708835602},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.43770310282707214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37008023262023926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2345079779624939},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18181157112121582},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.13596197962760925},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0685042142868042},{"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1819","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2048060899","https://openalex.org/W2079735306","https://openalex.org/W2134800885","https://openalex.org/W2148099973","https://openalex.org/W2184045248","https://openalex.org/W2193413348","https://openalex.org/W2284050935","https://openalex.org/W2407080277","https://openalex.org/W2423557781","https://openalex.org/W2520160253","https://openalex.org/W2530876040","https://openalex.org/W2567070169","https://openalex.org/W2755543420","https://openalex.org/W2763421725","https://openalex.org/W2782451907","https://openalex.org/W2799800213","https://openalex.org/W2888867175","https://openalex.org/W2888907095","https://openalex.org/W2889163603","https://openalex.org/W2889282842","https://openalex.org/W2898181186","https://openalex.org/W2904818793","https://openalex.org/W2906625520","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2945697643","https://openalex.org/W2962949994","https://openalex.org/W2963403664","https://openalex.org/W2963446712","https://openalex.org/W2963827914","https://openalex.org/W2964277995","https://openalex.org/W4297818305"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W1521968289","https://openalex.org/W4386269615","https://openalex.org/W2782041652","https://openalex.org/W2952088488","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2114916462","https://openalex.org/W4287547264","https://openalex.org/W3127565211"],"abstract_inverted_index":{"In":[0],"this":[1,67],"paper":[2],"we":[3,34,44,69],"report":[4,94],"state-of-the-art":[5],"results":[6,96],"on":[7,90,97],"LibriSpeech":[8,91],"among":[9],"end-to-end":[10],"speech":[11],"recognition":[12],"models":[13],"without":[14],"any":[15],"external":[16,79],"training":[17],"data.Our":[18],"model,":[19],"Jasper,":[20],"uses":[21,63],"only":[22],"1D":[23],"convolutions,":[24],"batch":[25],"normalization,":[26],"ReLU,":[27],"dropout,":[28],"and":[29,83,101],"residual":[30],"connections.To":[31],"improve":[32],"training,":[33],"further":[35],"introduce":[36],"a":[37,74,87],"new":[38],"layer-wise":[39],"optimizer":[40],"called":[41],"NovoGrad.Through":[42],"experiments,":[43],"demonstrate":[45],"that":[46],"the":[47,102],"proposed":[48],"deep":[49],"architecture":[50],"performs":[51],"as":[52],"well":[53],"or":[54],"better":[55],"than":[56],"more":[57],"complex":[58],"choices.Our":[59],"deepest":[60],"Jasper":[61],"variant":[62],"54":[64],"convolutional":[65],"layers.With":[66],"architecture,":[68],"achieve":[70],"2.95%":[71],"WER":[72,85],"using":[73],"beam-search":[75],"decoder":[76,89],"with":[77,86],"an":[78],"neural":[80],"language":[81],"model":[82],"3.86%":[84],"greedy":[88],"test-clean.We":[92],"also":[93],"competitive":[95],"Wall":[98],"Street":[99],"Journal":[100],"Hub5'00":[103],"conversational":[104],"evaluation":[105],"datasets.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":44},{"year":2019,"cited_by_count":14}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}