{"id":"https://openalex.org/W3008812308","doi":"https://doi.org/10.1109/asru46091.2019.9003898","title":"Simplified LSTMS for Speech Recognition","display_name":"Simplified LSTMS for Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008812308","doi":"https://doi.org/10.1109/asru46091.2019.9003898","mag":"3008812308"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003898","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoltan Tuske","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"547","last_page":"553"},"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.777813196182251},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.7702145576477051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6915370225906372},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6108436584472656},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.49586352705955505},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4488735496997833},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.44496843218803406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40183955430984497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37272369861602783},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.3717406988143921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777813196182251},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.7702145576477051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6915370225906372},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6108436584472656},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.49586352705955505},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4488735496997833},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.44496843218803406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40183955430984497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37272369861602783},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3717406988143921},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003898","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W194249466","https://openalex.org/W581956982","https://openalex.org/W1499864241","https://openalex.org/W1689711448","https://openalex.org/W2057653135","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2095705004","https://openalex.org/W2103584254","https://openalex.org/W2114016253","https://openalex.org/W2116261113","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2166312020","https://openalex.org/W2175402905","https://openalex.org/W2193413348","https://openalex.org/W2319453305","https://openalex.org/W2396384435","https://openalex.org/W2400505028","https://openalex.org/W2751185861","https://openalex.org/W2782451907","https://openalex.org/W2788402229","https://openalex.org/W2794209590","https://openalex.org/W2799800213","https://openalex.org/W2888957211","https://openalex.org/W2889282842","https://openalex.org/W2891942459","https://openalex.org/W2892090442","https://openalex.org/W2899771611","https://openalex.org/W2916979304","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2952410051","https://openalex.org/W2962760690","https://openalex.org/W2962832505","https://openalex.org/W2963042606","https://openalex.org/W2972692349","https://openalex.org/W3104896896","https://openalex.org/W4285719527","https://openalex.org/W4299838440","https://openalex.org/W6600213771","https://openalex.org/W6607862964","https://openalex.org/W6616837769","https://openalex.org/W6674330103","https://openalex.org/W6685537299","https://openalex.org/W6687566353","https://openalex.org/W6712772800","https://openalex.org/W6742632731","https://openalex.org/W6754522980","https://openalex.org/W6755212716","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2076209296","https://openalex.org/W2912153778","https://openalex.org/W4288108708","https://openalex.org/W4387163678","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W3173606726"],"abstract_inverted_index":{"In":[0,19,152],"this":[1],"paper":[2],"we":[3,21],"explore":[4],"new":[5],"variants":[6],"of":[7,16,85,148],"Long":[8],"Short-Term":[9],"Memory":[10],"(LSTM)":[11],"networks":[12],"for":[13,68,119],"sequential":[14],"modeling":[15],"acoustic":[17,124],"features.":[18],"particular,":[20],"show":[22],"that:":[23],"(i)":[24],"removing":[25],"the":[26,31,36,45,82,143,155],"output":[27,38],"gate,":[28],"(ii)":[29],"replacing":[30],"hyperbolic":[32],"tangent":[33],"nonlinearity":[34],"at":[35],"cell":[37,46],"with":[39,81],"hard":[40],"tanh,":[41],"and":[42,47,60,101,122,142],"(iii)":[43],"collapsing":[44],"hidden":[48],"state":[49],"vectors":[50],"leads":[51],"to":[52,64,95,111],"a":[53,65,103],"model":[54,73],"that":[55],"is":[56],"conceptually":[57,168],"simpler":[58],"than":[59,78,163],"comparable":[61],"in":[62,98],"effectiveness":[63],"regular":[66,164],"LSTM":[67,80],"speech":[69],"recognition.":[70],"The":[71],"proposed":[72,156],"has":[74,91],"25%":[75],"fewer":[76,109],"parameters":[77],"an":[79],"same":[83],"number":[84],"cells,":[86],"trains":[87],"faster":[88],"because":[89,106],"it":[90],"larger":[92,96],"gradients":[93],"leading":[94],"steps":[97],"weight":[99],"space,":[100],"reaches":[102],"better":[104,161],"optimum":[105],"there":[107],"are":[108],"nonlinearities":[110],"traverse":[112],"across":[113],"layers.":[114],"We":[115],"report":[116],"experimental":[117],"results":[118],"both":[120],"hybrid":[121],"CTC":[123],"models":[125,157],"on":[126],"three":[127],"publicly":[128],"available":[129],"English":[130],"datasets:":[131],"Switchboard":[132],"300":[133],"hours":[134,138,146],"telephone":[135],"conversations,":[136],"400":[137],"broadcast":[139],"news":[140],"transcription,":[141],"MALACH":[144],"176":[145],"corpus":[147],"Holocaust":[149],"survivor":[150],"testimonies.":[151],"all":[153],"cases":[154],"achieve":[158],"similar":[159],"or":[160],"accuracy":[162],"LSTMs":[165],"while":[166],"being":[167],"simpler.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}