{"id":"https://openalex.org/W2963211739","doi":"https://doi.org/10.1109/asru.2015.7404790","title":"EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding","display_name":"EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2963211739","doi":"https://doi.org/10.1109/asru.2015.7404790","mag":"2963211739"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088091232","display_name":"Mohammad Gowayyed","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Gowayyed","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":38.8891,"has_fulltext":false,"cited_by_count":640,"citation_normalized_percentile":{"value":0.99881197,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9977999925613403,"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":0.8336865305900574},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7927569150924683},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7679433822631836},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7211248874664307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.65372234582901},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6305649280548096},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6177448034286499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5394827127456665},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5341939330101013},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.519917905330658},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5082680583000183},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4624386727809906},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45251017808914185},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42021897435188293},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4161129593849182},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4127592444419861},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3762611448764801},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11322805285453796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06729716062545776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336865305900574},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7927569150924683},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7679433822631836},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7211248874664307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.65372234582901},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6305649280548096},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6177448034286499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5394827127456665},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5341939330101013},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.519917905330658},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5082680583000183},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4624386727809906},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45251017808914185},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42021897435188293},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4161129593849182},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4127592444419861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3762611448764801},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11322805285453796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06729716062545776},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W567546468","https://openalex.org/W587565084","https://openalex.org/W619799124","https://openalex.org/W1524333225","https://openalex.org/W1533416326","https://openalex.org/W1582482241","https://openalex.org/W1586532344","https://openalex.org/W1600744878","https://openalex.org/W1710082047","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W1986184096","https://openalex.org/W2005708641","https://openalex.org/W2010362084","https://openalex.org/W2033310064","https://openalex.org/W2046932483","https://openalex.org/W2048526313","https://openalex.org/W2064675550","https://openalex.org/W2087006792","https://openalex.org/W2102113734","https://openalex.org/W2107878631","https://openalex.org/W2117671523","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2134756243","https://openalex.org/W2136922672","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2161012272","https://openalex.org/W2293634267","https://openalex.org/W2293858598","https://openalex.org/W2397569915","https://openalex.org/W2403524927","https://openalex.org/W2407648438","https://openalex.org/W2898360541","https://openalex.org/W2962826786","https://openalex.org/W4285719527","https://openalex.org/W6615969787","https://openalex.org/W6617215739","https://openalex.org/W6619536949","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6639156005","https://openalex.org/W6640090968","https://openalex.org/W6658850935","https://openalex.org/W6675365184","https://openalex.org/W6676562027","https://openalex.org/W6696934422","https://openalex.org/W6713047518","https://openalex.org/W6713292810"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4398173524","https://openalex.org/W4290708361"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,14,104,122],"automatic":[3],"speech":[4,97],"recognition":[5],"(ASR)":[6],"has":[7],"improved":[8],"tremendously":[9],"due":[10],"to":[11,52,92],"the":[12,49,77,85,94,119,135,149],"application":[13],"deep":[15],"neural":[16,66],"networks":[17],"(DNNs).":[18],"Despite":[19],"this":[20],"progress,":[21],"building":[22],"a":[23,28,63,107],"new":[24],"ASR":[25,55],"system":[26],"remains":[27],"challenging":[29],"task,":[30],"requiring":[31],"various":[32],"resources,":[33],"multiple":[34],"training":[35],"stages":[36],"and":[37,98,124],"significant":[38],"expertise.":[39],"This":[40],"paper":[41],"presents":[42],"our":[43],"Eesen":[44,60,105,140],"framework":[45],"which":[46,117],"drastically":[47],"simplifies":[48],"existing":[50],"pipeline":[51],"build":[53],"state-of-the-art":[54],"systems.":[56],"Acoustic":[57],"modeling":[58],"in":[59],"involves":[61],"learning":[62],"single":[64],"recurrent":[65],"network":[67],"(RNN)":[68],"predicting":[69],"context-independent":[70],"targets":[71],"(phonemes":[72],"or":[73],"characters).":[74],"To":[75],"remove":[76],"need":[78],"for":[79],"pre-generated":[80],"frame":[81],"labels,":[82],"we":[83],"adopt":[84],"connectionist":[86],"temporal":[87],"classification":[88],"(CTC)":[89],"objective":[90],"function":[91],"infer":[93],"alignments":[95],"between":[96],"label":[99],"sequences.":[100],"A":[101],"distinctive":[102],"feature":[103],"is":[106],"generalized":[108],"decoding":[109,154],"approach":[110],"based":[111],"on":[112],"weighted":[113],"finite-state":[114],"transducers":[115],"(WFSTs),":[116],"enables":[118],"efficient":[120],"incorporation":[121],"lexicons":[123],"language":[125],"models":[126],"into":[127],"CTC":[128],"decoding.":[129],"Experiments":[130],"show":[131],"that":[132],"compared":[133],"with":[134],"standard":[136],"hybrid":[137],"DNN":[138],"systems,":[139],"achieves":[141],"comparable":[142],"word":[143],"error":[144],"rates":[145],"(WERs),":[146],"while":[147],"at":[148],"same":[150],"time":[151],"speeding":[152],"up":[153],"significantly.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":50},{"year":2021,"cited_by_count":67},{"year":2020,"cited_by_count":85},{"year":2019,"cited_by_count":138},{"year":2018,"cited_by_count":89},{"year":2017,"cited_by_count":67},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}