{"id":"https://openalex.org/W2754219472","doi":"https://doi.org/10.1109/jstsp.2017.2752691","title":"Inverted Alignments for End-to-End Automatic Speech Recognition","display_name":"Inverted Alignments for End-to-End Automatic Speech Recognition","publication_year":2017,"publication_date":"2017-09-14","ids":{"openalex":"https://openalex.org/W2754219472","doi":"https://doi.org/10.1109/jstsp.2017.2752691","mag":"2754219472"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2017.2752691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2752691","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3454087","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082582385","display_name":"Patrick Doetsch","orcid":"https://orcid.org/0000-0003-0359-3027"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Patrick Doetsch","raw_affiliation_strings":["Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110926453","display_name":"Mirko Hannemann","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mirko Hannemann","raw_affiliation_strings":["Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl fur Informatik VI, Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082582385"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.0382,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83412173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":"8","first_page":"1265","last_page":"1273"},"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8702300190925598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8175973892211914},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8116626143455505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7006183862686157},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6604893803596497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5492952466011047},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.533094584941864},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5027115345001221},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.45632269978523254},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4493350684642792},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43948209285736084},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4353584945201874},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4322007894515991},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3575526475906372},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16051903367042542}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8702300190925598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175973892211914},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8116626143455505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7006183862686157},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6604893803596497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492952466011047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.533094584941864},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5027115345001221},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.45632269978523254},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4493350684642792},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43948209285736084},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4353584945201874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4322007894515991},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3575526475906372},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16051903367042542},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jstsp.2017.2752691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2752691","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:publications.rwth-aachen.de:711585","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/711585","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE journal of selected topics in signal processing 11(8), 1265-1273 (2017). doi:10.1109/JSTSP.2017.2752691","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:3454087","is_oa":true,"landing_page_url":"https://zenodo.org/record/3454087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3454087","is_oa":true,"landing_page_url":"https://zenodo.org/record/3454087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"},{"id":"https://openalex.org/F4320324816","display_name":"Universit\u00e4t Paderborn","ror":"https://ror.org/058kzsd48"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320334679","display_name":"Research Executive Agency","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W66978610","https://openalex.org/W854541894","https://openalex.org/W1533416326","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1810943226","https://openalex.org/W1828163288","https://openalex.org/W1902237438","https://openalex.org/W1922655562","https://openalex.org/W1942035323","https://openalex.org/W1986184096","https://openalex.org/W1994396704","https://openalex.org/W2048608953","https://openalex.org/W2064675550","https://openalex.org/W2083393647","https://openalex.org/W2101596234","https://openalex.org/W2102113734","https://openalex.org/W2111535841","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133676762","https://openalex.org/W2143612262","https://openalex.org/W2152051032","https://openalex.org/W2165712214","https://openalex.org/W2193413348","https://openalex.org/W2287914047","https://openalex.org/W2289394825","https://openalex.org/W2291282366","https://openalex.org/W2327501763","https://openalex.org/W2395342389","https://openalex.org/W2404463488","https://openalex.org/W2404974730","https://openalex.org/W2491408735","https://openalex.org/W2514741789","https://openalex.org/W2515801922","https://openalex.org/W2516457973","https://openalex.org/W2526425061","https://openalex.org/W2533523411","https://openalex.org/W2559260703","https://openalex.org/W2748816379","https://openalex.org/W2755453684","https://openalex.org/W2905489173","https://openalex.org/W2949888546","https://openalex.org/W2952470929","https://openalex.org/W2962728618","https://openalex.org/W2962826786","https://openalex.org/W2962875366","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963399332","https://openalex.org/W2963688273","https://openalex.org/W2963729263","https://openalex.org/W2963795358","https://openalex.org/W2963833497","https://openalex.org/W2963920996","https://openalex.org/W2964260331","https://openalex.org/W6602736415","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6635078382","https://openalex.org/W6638273328","https://openalex.org/W6638749077","https://openalex.org/W6640090968","https://openalex.org/W6640708543","https://openalex.org/W6675280436","https://openalex.org/W6675365184","https://openalex.org/W6679436768","https://openalex.org/W6696116229","https://openalex.org/W6713140504","https://openalex.org/W6713561562","https://openalex.org/W6723310180","https://openalex.org/W6728030952","https://openalex.org/W6728841359","https://openalex.org/W6729544866","https://openalex.org/W6735593169","https://openalex.org/W6766224279"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W2395910192","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2112752961","https://openalex.org/W2128027845","https://openalex.org/W2113687551","https://openalex.org/W4386184937","https://openalex.org/W4394728283","https://openalex.org/W1493875009"],"abstract_inverted_index":{"In":[0],"this":[1,130],"paper,":[2],"we":[3,44,168],"propose":[4,45],"an":[5,52,68,82,139],"inverted":[6,140,174],"alignment":[7,84,175],"approach":[8,87],"for":[9,106],"sequence":[10,56],"classification":[11],"systems":[12],"like":[13],"automatic":[14],"speech":[15],"recognition":[16],"(ASR)":[17],"that":[18,72,167],"naturally":[19],"incorporates":[20],"discriminative,":[21],"artificial-neural-network-based":[22],"label":[23,34,55],"distributions.":[24],"Instead":[25],"of":[26,51,61,109,115,129,135],"aligning":[27],"each":[28,49],"input":[29,64],"frame":[30],"to":[31,46,57,151],"a":[32,58,95,101,107],"state":[33,54],"as":[35],"in":[36],"the":[37,91,127,133,144,159],"standard":[38,152],"hidden":[39],"Markov":[40],"model":[41,71,99,110],"(HMM)":[42],"derivation,":[43],"inversely":[47],"align":[48],"element":[50],"HMM":[53],"segment-wise":[59],"encoding":[60],"several":[62],"consecutive":[63],"frames.":[65],"This":[66],"enables":[67],"integrated":[69,136],"discriminative":[70],"can":[73,169],"be":[74],"trained":[75],"end-to-end":[76],"from":[77,81],"scratch":[78],"or":[79],"starting":[80],"existing":[83],"path.":[85],"The":[86],"does":[88],"not":[89],"assume":[90],"usual":[92],"decomposition":[93],"into":[94],"separate":[96],"(generative)":[97],"acoustic":[98,145],"and":[100,104,138,176],"language":[102],"model,":[103],"allows":[105],"variety":[108],"assumptions,":[111],"including":[112],"statistical":[113],"variants":[114],"attention.":[116],"Following":[117],"our":[118],"initial":[119],"paper":[120,131],"with":[121,173],"proof-of-concept":[122],"experiments":[123,157],"on":[124,158],"handwriting":[125],"recognition,":[126],"focus":[128],"was":[132],"investigation":[134],"training":[137],"decoding":[141,177],"approach,":[142],"whereas":[143],"modeling":[146],"still":[147],"remains":[148],"largely":[149],"similar":[150],"hybrid":[153],"modeling.":[154],"We":[155],"provide":[156],"CHiME-4":[160],"noisy":[161],"ASR":[162],"task.":[163],"Our":[164],"results":[165,172],"show":[166],"reach":[170],"competitive":[171],"strategies.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}