{"id":"https://openalex.org/W3095838132","doi":"https://doi.org/10.21437/interspeech.2020-2947","title":"ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition","display_name":"ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095838132","doi":"https://doi.org/10.21437/interspeech.2020-2947","mag":"3095838132"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2947","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101875418","display_name":"Jing Pan","orcid":"https://orcid.org/0000-0002-5178-2247"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jing Pan","raw_affiliation_strings":["ASAPP Inc"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076769170","display_name":"Joshua Shapiro","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Shapiro","raw_affiliation_strings":["ASAPP Inc"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082461467","display_name":"Jeremy Wohlwend","orcid":"https://orcid.org/0000-0002-1993-2380"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Wohlwend","raw_affiliation_strings":["ASAPP Inc"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyu J. Han","raw_affiliation_strings":["ASAPP Inc"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030752617","display_name":"Tao Le\u00ed","orcid":"https://orcid.org/0000-0002-0900-1582"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Lei","raw_affiliation_strings":["ASAPP Inc"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101774785","display_name":"Tao Ma","orcid":"https://orcid.org/0000-0001-6135-9736"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Ma","raw_affiliation_strings":["ASAPP Inc"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101875418"],"corresponding_institution_ids":["https://openalex.org/I1283576576"],"apc_list":null,"apc_paid":null,"fwci":2.9163,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92676502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9926000237464905,"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":0.9904999732971191,"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/speech-recognition","display_name":"Speech recognition","score":0.7104588150978088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7037073373794556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39457863569259644}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7104588150978088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037073373794556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39457863569259644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2947","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1528470941","https://openalex.org/W1597121597","https://openalex.org/W1686810756","https://openalex.org/W2002342963","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2515863432","https://openalex.org/W2533523411","https://openalex.org/W2567070169","https://openalex.org/W2749066063","https://openalex.org/W2782451907","https://openalex.org/W2888867175","https://openalex.org/W2889129873","https://openalex.org/W2889152503","https://openalex.org/W2892090442","https://openalex.org/W2916979304","https://openalex.org/W2936774411","https://openalex.org/W2963266252","https://openalex.org/W2964286182","https://openalex.org/W2975044525","https://openalex.org/W2981857663","https://openalex.org/W2991213871","https://openalex.org/W3015446641","https://openalex.org/W3015960524","https://openalex.org/W3016010032","https://openalex.org/W3095173472","https://openalex.org/W3103005696","https://openalex.org/W3163211337","https://openalex.org/W4288265053","https://openalex.org/W4292356195","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"state-of-the-art":[5],"(SOTA)":[6],"performance":[7,88],"on":[8,79,83,104,108],"the":[9,34,38,64,87],"LibriSpeech":[10],"corpus":[11],"with":[12,63],"two":[13],"novel":[14],"neural":[15],"network":[16],"architectures,":[17],"a":[18,25,57,94],"multistream":[19,39],"CNN":[20,40],"for":[21,31,61],"acoustic":[22,41],"modeling":[23],"and":[24,81,106],"selfattentive":[26],"simple":[27],"recurrent":[28],"unit":[29],"(SRU)":[30],"language":[32,98],"modeling.In":[33],"hybrid":[35],"ASR":[36],"framework,":[37],"model":[42],"processes":[43],"an":[44],"input":[45],"of":[46,77,102],"speech":[47],"frames":[48],"in":[49],"multiple":[50],"parallel":[51],"pipelines":[52],"where":[53],"each":[54],"stream":[55],"has":[56],"unique":[58],"dilation":[59],"rate":[60,74],"diversity.Trained":[62],"SpecAugment":[65],"data":[66],"augmentation":[67],"method,":[68],"it":[69],"achieves":[70],"relative":[71],"word":[72],"error":[73],"(WER)":[75],"improvements":[76],"4%":[78],"test-clean":[80,105],"14%":[82],"test-other.We":[84],"further":[85],"improve":[86],"via":[89],"N":[90],"-best":[91],"rescoring":[92],"using":[93],"24-layer":[95],"self-attentive":[96],"SRU":[97],"model,":[99],"achieving":[100],"WERs":[101],"1.75%":[103],"4.46%":[107],"test-other.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3}],"updated_date":"2026-02-21T06:11:54.161237","created_date":"2025-10-10T00:00:00"}