{"id":"https://openalex.org/W3015758192","doi":"https://doi.org/10.1109/icassp40776.2020.9053635","title":"Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR","display_name":"Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015758192","doi":"https://doi.org/10.1109/icassp40776.2020.9053635","mag":"3015758192"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5060987315","display_name":"Mohammad Zeineldeen","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":true,"raw_author_name":"Mohammad Zeineldeen","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059521407","display_name":"Albert Zeyer","orcid":"https://orcid.org/0000-0002-6655-671X"},"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":"Albert Zeyer","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, 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":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, 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":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060987315"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77694596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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/T12676","display_name":"Machine Learning and ELM","score":0.995199978351593,"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/T12169","display_name":"Non-Destructive Testing Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8308340311050415},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6994386911392212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6452288627624512},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6106714010238647},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5260772109031677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3664405047893524},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06564337015151978}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8308340311050415},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6994386911392212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452288627624512},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6106714010238647},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5260772109031677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3664405047893524},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06564337015151978},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W2009150118","https://openalex.org/W2064675550","https://openalex.org/W2163922914","https://openalex.org/W2166637769","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2402144811","https://openalex.org/W2471933213","https://openalex.org/W2588610957","https://openalex.org/W2799800213","https://openalex.org/W2799923439","https://openalex.org/W2905263927","https://openalex.org/W2905489173","https://openalex.org/W2907121943","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2949117887","https://openalex.org/W2953384591","https://openalex.org/W2962784628","https://openalex.org/W2962949994","https://openalex.org/W2963304263","https://openalex.org/W2963403868","https://openalex.org/W2963542740","https://openalex.org/W2963596039","https://openalex.org/W2963685250","https://openalex.org/W2964045208","https://openalex.org/W3008191852","https://openalex.org/W3105532142","https://openalex.org/W4288621368","https://openalex.org/W4302375066","https://openalex.org/W4385245566","https://openalex.org/W6604254268","https://openalex.org/W6631943919","https://openalex.org/W6638667902","https://openalex.org/W6684440257","https://openalex.org/W6695676441","https://openalex.org/W6701650085","https://openalex.org/W6713134421","https://openalex.org/W6720589053","https://openalex.org/W6733590821","https://openalex.org/W6739901393","https://openalex.org/W6749954789","https://openalex.org/W6757468910","https://openalex.org/W6757717501","https://openalex.org/W6757856092","https://openalex.org/W6780226713","https://openalex.org/W6780493881","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Training":[0],"deep":[1,36],"neural":[2,48],"networks":[3,49],"is":[4,65],"often":[5,13],"challenging":[6],"in":[7,34,145],"terms":[8],"of":[9,58,62],"training":[10,35],"stability.":[11],"It":[12],"requires":[14,110],"careful":[15],"hyperparameter":[16,112],"tuning":[17],"or":[18],"a":[19,31,141],"pretraining":[20],"scheme":[21],"to":[22,29,55,105,125],"converge.":[23],"Layer":[24],"normalization":[25],"(LN)":[26],"has":[27],"shown":[28],"be":[30],"crucial":[32],"ingredient":[33],"encoder-decoder":[37],"models.":[38],"We":[39,72,120],"explore":[40],"various":[41],"LN":[42,54,92,124],"long":[43],"short-term":[44],"memory":[45],"(LSTM)":[46],"recurrent":[47,129],"(RNN)":[50],"variants":[51],"by":[52,135],"applying":[53,123],"different":[56],"parts":[57],"the":[59,77,94,100],"internal":[60],"recurrency":[61],"LSTMs.":[63],"There":[64],"no":[66],"previous":[67],"work":[68],"that":[69,91,122],"investigates":[70],"this.":[71],"carry":[73],"out":[74],"experiments":[75],"on":[76],"Switchboard":[78],"300h":[79],"task":[80],"for":[81],"both":[82,126],"hybrid":[83],"and":[84,88,114,128],"end-to-end":[85],"ASR":[86],"models":[87],"we":[89,133],"show":[90],"improves":[93],"final":[95],"word":[96],"error":[97],"rate":[98],"(WER),":[99],"stability":[101],"during":[102],"training,":[103],"allows":[104],"train":[106],"even":[107,117],"deeper":[108],"models,":[109],"less":[111],"tuning,":[113],"works":[115],"well":[116],"without":[118],"pre-training.":[119],"find":[121],"forward":[127],"inputs":[130],"globally,":[131],"which":[132],"denoted":[134],"Global":[136],"Joined":[137],"Norm":[138],"variant,":[139],"gives":[140],"10%":[142],"relative":[143],"improvement":[144],"WER.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}