{"id":"https://openalex.org/W3015265920","doi":"https://doi.org/10.1109/icassp40776.2020.9053176","title":"Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition","display_name":"Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015265920","doi":"https://doi.org/10.1109/icassp40776.2020.9053176","mag":"3015265920"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/1912.01679","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109397773","display_name":"Shaoshi Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaoshi Ling","raw_affiliation_strings":["Amazon AWS AI"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000919546","display_name":"Yuzong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzong Liu","raw_affiliation_strings":["Amazon AWS AI"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037283647","display_name":"Juli\u00e1n Salazar","orcid":"https://orcid.org/0000-0003-0943-7594"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Salazar","raw_affiliation_strings":["Amazon AWS AI"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Amazon AWS AI"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109397773"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":16.5932,"has_fulltext":false,"cited_by_count":148,"citation_normalized_percentile":{"value":0.99318706,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.7486761808395386},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7365542054176331},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6501352190971375},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6324734687805176},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5920008420944214},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5799857378005981},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4983391761779785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.463748037815094},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4268709719181061},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2653973400592804},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.23051929473876953},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08564755320549011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486761808395386},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7365542054176331},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6501352190971375},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6324734687805176},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5920008420944214},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5799857378005981},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4983391761779785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.463748037815094},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4268709719181061},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2653973400592804},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.23051929473876953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08564755320549011},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.01679","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.01679","pdf_url":"https://arxiv.org/pdf/1912.01679","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:1912.01679","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.01679","pdf_url":"https://arxiv.org/pdf/1912.01679","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W176510440","https://openalex.org/W1993660824","https://openalex.org/W2110798204","https://openalex.org/W2124558353","https://openalex.org/W2127141656","https://openalex.org/W2127499922","https://openalex.org/W2136922672","https://openalex.org/W2145494108","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2293363371","https://openalex.org/W2486109868","https://openalex.org/W2512655038","https://openalex.org/W2787560479","https://openalex.org/W2802248956","https://openalex.org/W2889213362","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2950813464","https://openalex.org/W2962739339","https://openalex.org/W2962753370","https://openalex.org/W2962907457","https://openalex.org/W2963211739","https://openalex.org/W2963341956","https://openalex.org/W2963425185","https://openalex.org/W2964245029","https://openalex.org/W2970597249","https://openalex.org/W2972889948","https://openalex.org/W2972943112","https://openalex.org/W2972981541","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2996383576","https://openalex.org/W3011411500","https://openalex.org/W3100270690","https://openalex.org/W3103005696","https://openalex.org/W3125709657","https://openalex.org/W6676481782","https://openalex.org/W6681588610","https://openalex.org/W6755207826","https://openalex.org/W6760911985","https://openalex.org/W6763701032","https://openalex.org/W6765807869","https://openalex.org/W6769196770"],"related_works":["https://openalex.org/W3021676282","https://openalex.org/W3008176773","https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2533508831","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W1911859126","https://openalex.org/W2158598479"],"abstract_inverted_index":{"We":[0,11],"propose":[1],"a":[2,14,27,51,57],"novel":[3],"approach":[4,99],"to":[5,49],"semi-supervised":[6],"automatic":[7],"speech":[8],"recognition":[9],"(ASR).":[10],"first":[12],"exploit":[13],"large":[15],"amount":[16,59,104],"of":[17,30,60,105,118],"unlabeled":[18],"audio":[19,62],"data":[20,107,120],"via":[21],"representation":[22],"learning,":[23],"where":[24],"we":[25,67],"reconstruct":[26],"temporal":[28],"slice":[29],"filterbank":[31,80],"features":[32],"from":[33],"past":[34],"and":[35,84,94],"future":[36],"context":[37],"frames.":[38],"The":[39],"resulting":[40],"deep":[41],"contextualized":[42],"acoustic":[43],"representations":[44],"(DeCoAR)":[45],"are":[46],"then":[47,113],"used":[48],"train":[50],"CTC-based":[52],"end-to-end":[53],"ASR":[54],"system":[55],"using":[56],"smaller":[58],"labeled":[61,106,119],"data.":[63],"In":[64],"our":[65],"experiments,":[66],"show":[68],"that":[69],"systems":[70],"trained":[71,77],"on":[72,78,91,111,123,127],"DeCoAR":[73],"consistently":[74],"outperform":[75],"ones":[76],"conventional":[79],"features,":[81],"giving":[82],"42%":[83],"19%":[85],"relative":[86],"improvement":[87],"over":[88],"the":[89,103],"baseline":[90],"WSJ":[92],"eval92":[93],"LibriSpeech":[95,112],"test-clean,":[96],"respectively.":[97],"Our":[98],"can":[100],"drastically":[101],"reduce":[102],"required;":[108],"unsupervised":[109],"training":[110,126],"supervision":[114],"with":[115,125],"100":[116],"hours":[117,130],"achieves":[121],"performance":[122],"par":[124],"all":[128],"960":[129],"directly.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}