{"id":"https://openalex.org/W3168770049","doi":"https://doi.org/10.1109/ieeeconf51394.2020.9443456","title":"A Review of On-Device Fully Neural End-to-End Automatic Speech Recognition Algorithms","display_name":"A Review of On-Device Fully Neural End-to-End Automatic Speech Recognition Algorithms","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3168770049","doi":"https://doi.org/10.1109/ieeeconf51394.2020.9443456","mag":"3168770049"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf51394.2020.9443456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf51394.2020.9443456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"review","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","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"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","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101652725","display_name":"Dongsoo Lee","orcid":"https://orcid.org/0000-0002-4155-6940"},"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":"Dongsoo Lee","raw_affiliation_strings":["Samsung Research,Seoul,South Korea","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396580","display_name":"Jiyeon Kim","orcid":"https://orcid.org/0000-0001-7964-5060"},"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":"Jiyeon Kim","raw_affiliation_strings":["Samsung Research,Seoul,South Korea","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053775185","display_name":"Ankur Kumar","orcid":"https://orcid.org/0000-0002-9248-1416"},"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":"Ankur Kumar","raw_affiliation_strings":["Samsung Research,Seoul,South Korea","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340036","display_name":"Sung-Soo Kim","orcid":"https://orcid.org/0000-0003-3207-4648"},"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":"Sungsoo Kim","raw_affiliation_strings":["Samsung Research,Seoul,South Korea","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"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","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"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","Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100684422"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":2.9163,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92745384,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"277","last_page":"283"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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":0.9943000078201294,"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":0.8051953315734863},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6386662721633911},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5512550473213196},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5506401658058167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5314592123031616},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5253913998603821},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5024056434631348},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4914499521255493},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4858102798461914},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4688825309276581},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43310391902923584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3549700677394867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33823826909065247},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3361818790435791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051953315734863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6386662721633911},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5512550473213196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5506401658058167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5314592123031616},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5253913998603821},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5024056434631348},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4914499521255493},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4858102798461914},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4688825309276581},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43310391902923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3549700677394867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33823826909065247},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3361818790435791},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf51394.2020.9443456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf51394.2020.9443456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1607274768","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2013305145","https://openalex.org/W2064675550","https://openalex.org/W2107508685","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2293829681","https://openalex.org/W2326699523","https://openalex.org/W2396889049","https://openalex.org/W2398042854","https://openalex.org/W2402144811","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2748679025","https://openalex.org/W2750499125","https://openalex.org/W2888779557","https://openalex.org/W2889129739","https://openalex.org/W2892090442","https://openalex.org/W2898997786","https://openalex.org/W2936774411","https://openalex.org/W2953384591","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963403868","https://openalex.org/W2963980003","https://openalex.org/W2964272710","https://openalex.org/W2964299589","https://openalex.org/W2972630480","https://openalex.org/W2972816482","https://openalex.org/W3007185811","https://openalex.org/W3007528493","https://openalex.org/W3008587939","https://openalex.org/W3095193086","https://openalex.org/W3095867028","https://openalex.org/W3096758108","https://openalex.org/W3097777922","https://openalex.org/W3152100107","https://openalex.org/W4294619417","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6679436768","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6747158283","https://openalex.org/W6754522980","https://openalex.org/W6756165562"],"related_works":["https://openalex.org/W3126788496","https://openalex.org/W2916997151","https://openalex.org/W3198455051","https://openalex.org/W2949174760","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W2888189389","https://openalex.org/W3164030209","https://openalex.org/W642007152"],"abstract_inverted_index":{"In":[0,158],"this":[1,159],"paper,":[2,160],"we":[3,161],"review":[4,162],"various":[5],"end-to-end":[6,99,164],"automatic":[7],"speech":[8,19,62,68,100,108,131,165],"recognition":[9,20,63,69,101,109,132,166],"algorithms":[10,102],"and":[11,55,134,174],"their":[12,92,152,171],"optimization":[13],"techniques":[14],"for":[15],"on-device":[16,93,153],"applications.":[17],"Conventional":[18],"systems":[21,110,141],"comprise":[22],"a":[23,34,37,40,45,49,71],"large":[24,73],"number":[25],"of":[26],"discrete":[27],"components":[28],"such":[29,66,163],"as":[30],"an":[31,42],"acoustic":[32],"model,":[33,36,39],"language":[35,74],"pronunciation":[38],"text-normalizer,":[41],"inverse-text":[43],"normalizer,":[44],"decoder":[46],"based":[47,111],"on":[48,112],"Weighted":[50],"Finite":[51],"State":[52],"Transducer":[53,120],"(WFST),":[54],"so":[56,135],"on.":[57,136],"To":[58],"obtain":[59],"sufficiently":[60],"high":[61],"accuracy":[64],"with":[65],"conventional":[67,149,178],"systems,":[70,133],"very":[72],"model":[75],"(up":[76],"to":[77,148,177],"100":[78],"GB)":[79],"is":[80],"usually":[81],"needed.":[82],"Hence,":[83],"the":[84],"corresponding":[85],"WFST":[86],"size":[87],"becomes":[88],"enormous,":[89],"which":[90],"prohibits":[91],"implementation.":[94],"Recently,":[95],"fully":[96,138],"neural":[97,139],"network":[98],"have":[103],"been":[104],"proposed.":[105],"Examples":[106],"include":[107],"Connectionist":[113],"Temporal":[114],"Classification":[115],"(CTC),":[116],"Recurrent":[117],"Neural":[118],"Network":[119],"(RNN-T),":[121],"Attention-based":[122],"Encoder-Decoder":[123],"models":[124],"(AED),":[125],"Monotonic":[126],"Chunk-wise":[127],"Attention":[128],"(MoChA),":[129],"transformer-based":[130],"These":[137],"network-based":[140],"require":[142],"much":[143],"smaller":[144],"memory":[145],"footprints":[146],"compared":[147,176],"algorithms,":[150],"therefore":[151],"implementation":[154],"has":[155],"become":[156],"feasible.":[157],"models.":[167],"We":[168],"extensively":[169],"discuss":[170],"structures,":[172],"performance,":[173],"advantages":[175],"algorithms.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}