乐胖代购免代理版

{"id":"https://openalex.org/W3140910706","doi":"https://doi.org/10.1109/slt48900.2021.9383621","title":"Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR","display_name":"Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3140910706","doi":"https://doi.org/10.1109/slt48900.2021.9383621","mag":"3140910706"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383621","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2102.03055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100760516","display_name":"Ruizhi Li","orcid":"https://orcid.org/0000-0002-2496-5224"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"funder","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhi Li","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046596198","display_name":"Gregory Sell","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"funder","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Sell","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"funder","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.098,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":56,"max":66},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"235"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9997,"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":0.998,"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/robustness","display_name":"Robustness","score":0.7769407},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49005544},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.48330522},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.48186788},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream Processing","score":0.4412716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942082},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7769407},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.50551605},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49005544},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.48330522},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.48186788},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.476396},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.4412716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4349987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42889974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36766684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2585239},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383621","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.03055","pdf_url":"http://arxiv.org/pdf/2102.03055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.03055","pdf_url":"http://arxiv.org/pdf/2102.03055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W2125336414","https://openalex.org/W2144121180","https://openalex.org/W2144499799","https://openalex.org/W2148613904","https://openalex.org/W2397147568","https://openalex.org/W2526425061","https://openalex.org/W2581377246","https://openalex.org/W2587464121","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2886180730","https://openalex.org/W2889508099","https://openalex.org/W2894835365","https://openalex.org/W2899640612","https://openalex.org/W2900070823","https://openalex.org/W2900091092","https://openalex.org/W2900092534","https://openalex.org/W2904113148","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962866381","https://openalex.org/W2963064586","https://openalex.org/W2964012862","https://openalex.org/W2964391865","https://openalex.org/W2972721952","https://openalex.org/W2995025901","https://openalex.org/W3016010944","https://openalex.org/W4297798436","https://openalex.org/W854541894"],"related_works":["https://openalex.org/W52257553","https://openalex.org/W4281746777","https://openalex.org/W2886490431","https://openalex.org/W2753968464","https://openalex.org/W2523233245","https://openalex.org/W2294347781","https://openalex.org/W216646892","https://openalex.org/W2132367116","https://openalex.org/W2125696272","https://openalex.org/W1512114968"],"abstract_inverted_index":{"Performance":[0],"degradation":[1],"of":[2,48,52,122,145,179],"an":[3,89],"Automatic":[4],"Speech":[5],"Recognition":[6],"(ASR)":[7],"system":[8],"is":[9,17,23],"commonly":[10],"observed":[11],"when":[12],"the":[13,74,143,165],"test":[14],"acoustic":[15],"condition":[16],"different":[18],"from":[19,79],"training.":[20],"Hence,":[21],"it":[22],"essential":[24],"to":[25,104,126],"make":[26],"ASR":[27],"systems":[28],"robust":[29],"against":[30],"various":[31],"environmental":[32],"distortions,":[33],"such":[34],"as":[35,88,159],"background":[36],"noises":[37],"and":[38,56,157],"reverberations.":[39],"In":[40,85],"a":[41,50,60,93,160],"multi-stream":[42,68,75,161],"paradigm,":[43],"improving":[44],"robustness":[45],"takes":[46],"account":[47],"handling":[49],"variety":[51],"unseen":[53,185],"single-stream":[54,106],"conditions":[55],"inter-stream":[57],"dynamics.":[58],"Previously,":[59],"practical":[61],"two-stage":[62,94],"training":[63,167],"strategy":[64],"was":[65],"proposed":[66],"within":[67],"end-to-end":[69],"ASR,":[70],"where":[71],"Stage-2":[72,113],"formulates":[73],"model":[76],"with":[77,109,142,164,173],"features":[78,121],"Stage-1":[80,101],"Universal":[81],"Feature":[82],"Extractor":[83],"(UFE).":[84],"this":[86],"paper,":[87],"extension,":[90],"we":[91,133],"introduce":[92],"augmentation":[95,111],"scheme":[96],"focusing":[97],"on":[98,119,153],"mismatch":[99],"scenarios:":[100],"Augmentation":[102],"aims":[103],"address":[105],"input":[107],"varieties":[108],"data":[110],"techniques;":[112],"Time":[114],"Masking":[115],"applies":[116],"temporal":[117],"masks":[118],"UFE":[120],"randomly":[123],"selected":[124],"streams":[125],"simulate":[127],"diverse":[128],"stream":[129,186],"combinations.":[130,187],"During":[131],"inference,":[132],"also":[134],"present":[135],"adaptive":[136],"Connectionist":[137],"Temporal":[138],"Classification":[139],"(CTC)":[140],"fusion":[141],"help":[144],"hierarchical":[146],"attention":[147],"mechanisms.":[148],"Experiments":[149],"have":[150],"been":[151],"conducted":[152],"two":[154],"datasets,":[155],"DIRHA":[156],"AMI,":[158],"scenario.":[162],"Compared":[163],"previous":[166],"strategy,":[168],"substantial":[169],"improvements":[170],"are":[171],"reported":[172],"relative":[174],"word":[175],"error":[176],"rate":[177],"reductions":[178],"29.7":[180],"-":[181],"59.3%":[182],"across":[183],"several":[184]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3140910706","counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-04-18T17:00:15.220041","created_date":"2021-04-13"}