{"id":"https://openalex.org/W3162308011","doi":"https://doi.org/10.1109/icassp39728.2021.9414117","title":"Streaming End-to-End Speech Recognition with Jointly Trained Neural Feature Enhancement","display_name":"Streaming End-to-End Speech Recognition with Jointly Trained Neural Feature Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162308011","doi":"https://doi.org/10.1109/icassp39728.2021.9414117","mag":"3162308011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043920881","display_name":"Abhinav Garg","orcid":"https://orcid.org/0000-0001-5082-5500"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Abhinav Garg","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101194806","display_name":"Changwoo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changwoo Han","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100684422"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77572151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6773","last_page":"6777"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.9947999715805054,"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":0.7605319023132324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7047127485275269},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6186105608940125},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6029995679855347},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5896547436714172},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5732277035713196},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5014772415161133},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.492603600025177},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.48067864775657654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4265826344490051},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33795398473739624},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1823306679725647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0826311707496643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605319023132324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7047127485275269},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6186105608940125},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6029995679855347},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5896547436714172},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5732277035713196},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5014772415161133},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.492603600025177},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.48067864775657654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4265826344490051},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33795398473739624},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1823306679725647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0826311707496643},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2107508685","https://openalex.org/W2127141656","https://openalex.org/W2296073425","https://openalex.org/W2326699523","https://openalex.org/W2396889049","https://openalex.org/W2526425061","https://openalex.org/W2617258110","https://openalex.org/W2962824709","https://openalex.org/W2963979492","https://openalex.org/W2963980003","https://openalex.org/W2964121744","https://openalex.org/W2964272710","https://openalex.org/W2972816482","https://openalex.org/W2972977747","https://openalex.org/W3007185811","https://openalex.org/W3007528493","https://openalex.org/W3008587939","https://openalex.org/W3095867028","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6738243166","https://openalex.org/W6747158283"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W1999612375","https://openalex.org/W2997094352","https://openalex.org/W2938107654","https://openalex.org/W3216976533"],"abstract_inverted_index":{"In":[0,146],"this":[1,41],"paper,":[2],"we":[3,87],"present":[4],"a":[5,36,67,76],"streaming":[6,28],"end-to-end":[7],"speech":[8,29,63,72],"recognition":[9,30,32,64],"model":[10,42,69,108,160],"based":[11],"on":[12,149],"Monotonic":[13],"Chunkwise":[14],"Attention":[15],"(MoCha)":[16],"jointly":[17],"trained":[18,111],"with":[19,31,161],"enhancement":[20,122],"layers.":[21],"Even":[22],"though":[23],"the":[24,50,107,116,121,128,131,138,150,158,170],"MoCha":[25],"attention":[26],"enables":[27],"accuracy":[33,65],"comparable":[34],"to":[35,45],"full":[37],"attention-based":[38],"approach,":[39],"training":[40,53,78,90,144,163,173],"is":[43,80,109],"sensitive":[44],"various":[46],"factors":[47],"such":[48],"as":[49,143],"difficulty":[51],"of":[52,60,66,94,101,118,130],"examples,":[54],"hyper-parameters,":[55],"and":[56,98,153],"so":[57],"on.":[58],"Because":[59],"these":[61],"issues,":[62],"MoCha-based":[68],"for":[70,137],"clean":[71,113],"drops":[73],"significantly":[74,166],"when":[75],"multi-style":[77,172],"approach":[79],"applied.":[81],"Inspired":[82],"by":[83],"Curriculum":[84],"Learning":[85],"[1],":[86],"introduce":[88],"two":[89],"strategies:":[91],"Gradual":[92,99],"Application":[93],"Enhanced":[95,102],"Features":[96],"(GAEF)":[97],"Reduction":[100],"Loss":[103],"(GREL).":[104],"With":[105,126],"GAEF,":[106],"initially":[110],"using":[112],"features.":[114],"Subsequently,":[115],"portion":[117,129],"outputs":[119],"from":[120],"layers":[123],"gradually":[124,141],"increases.":[125],"GREL,":[127],"Mean":[132],"Squared":[133],"Error":[134],"(MSE)":[135],"loss":[136],"enhanced":[139],"output":[140],"reduces":[142],"proceeds.":[145],"experimental":[147],"results":[148,168],"LibriSpeech":[151],"corpus":[152],"noisy":[154],"far-field":[155],"test":[156],"sets,":[157],"proposed":[159],"GAEF-GREL":[162],"strategies":[164],"shows":[165],"better":[167],"than":[169],"conventional":[171],"approach.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}