{"id":"https://openalex.org/W2811388227","doi":null,"title":"COMPARING GRU AND LSTM FOR AUTOMATIC SPEECH RECOGNITION","display_name":"COMPARING GRU AND LSTM FOR AUTOMATIC SPEECH RECOGNITION","publication_year":2016,"publication_date":"2016-01-30","ids":{"openalex":"https://openalex.org/W2811388227","mag":"2811388227"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-01633254v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01633254","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"[Research Report] LIG. 2016","raw_type":"info:eu-repo/semantics/report"},"parent_works":[],"lineage":["https://openalex.org/W2811388227"],"child_works_count":0,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01633254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012586106","display_name":"Shubham Khandelwal","orcid":"https://orcid.org/0000-0002-0151-1078","observed_orcids":["https://orcid.org/0000-0002-0151-1078","https://orcid.org/0000-0003-3165-1140"]},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Khandelwal, Shubham","raw_affiliation_strings":["GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","LIG  - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","institution_ids":["https://openalex.org/I4210104430"]},{"raw_affiliation_string":"LIG  - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113675850","display_name":"Benjamin Lecouteux","orcid":"https://orcid.org/0000-0003-3000-6190","observed_orcids":["https://orcid.org/0000-0003-3000-6190"]},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lecouteux, Benjamin","raw_affiliation_strings":["GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","LIG  - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","institution_ids":["https://openalex.org/I4210104430"]},{"raw_affiliation_string":"LIG  - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040820339","display_name":"Laurent Besacier","orcid":"https://orcid.org/0000-0001-7411-9125","observed_orcids":["https://orcid.org/0000-0001-7411-9125"]},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Besacier, Laurent","raw_affiliation_strings":["GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","LIG  - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","institution_ids":["https://openalex.org/I4210104430"]},{"raw_affiliation_string":"LIG  - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)","institution_ids":["https://openalex.org/I4210104430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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":0.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gated-recurrent-unit","display_name":"gated recurrent unit","score":0.9430000185966492},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"long short-term memory","score":0.9869999885559082},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7730000019073486},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.6919999718666077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8510000109672546},{"id":"https://openalex.org/keywords/ted-talks","display_name":"TED Talks","score":0.5640000104904175},{"id":"https://openalex.org/keywords/continuous-speech-recognition","display_name":"continuous speech recognition","score":0.7160000205039978},{"id":"https://openalex.org/keywords/bidirectional-gru","display_name":"bidirectional GRU","score":0.9459999799728394},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.9269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193409442901611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7830561399459839},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6476565599441528},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.611929714679718},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.597679853439331},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5356801152229309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222276449203491},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.51973557472229},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.46216249465942383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.452381432056427},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4388979375362396},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33286845684051514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32949137687683105},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-01633254v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01633254","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"[Research Report] LIG. 2016","raw_type":"info:eu-repo/semantics/report"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01633254v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01633254","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"[Research Report] LIG. 2016","raw_type":"info:eu-repo/semantics/report"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2970413753","https://openalex.org/W4387161991","https://openalex.org/W3188332469","https://openalex.org/W2971982237","https://openalex.org/W4391994148","https://openalex.org/W4221006962","https://openalex.org/W3126867788","https://openalex.org/W2794209590","https://openalex.org/W2613006358","https://openalex.org/W2749432513"],"abstract_inverted_index":{"This":[0,72],"paper":[1],"proposes":[2],"to":[3,48,52,97],"compare":[4],"Gated":[5],"Recurrent":[6],"Unit":[7],"(GRU)":[8],"and":[9,84,102,128],"Long":[10],"Short":[11],"Term":[12],"Memory":[13],"(LSTM)":[14],"for":[15,27,58],"speech":[16,30,39],"recognition":[17,40],"acoustic":[18],"models.":[19],"While":[20],"these":[21],"recurrent":[22],"models":[23,130],"were":[24],"mainly":[25],"proposed":[26],"simple":[28],"read":[29],"tasks,":[31],"we":[32],"experiment":[33],"on":[34,114,125],"a":[35,66,81,91,119],"large":[36],"vocabulary":[37],"continuous":[38],"task:":[41],"transcription":[42],"of":[43],"TED":[44],"talks.":[45],"In":[46],"addition":[47],"be":[49],"simpler":[50],"compared":[51],"LSTM,":[53],"GRU":[54,83],"networks":[55],"outperform":[56],"LSTM":[57],"all":[59],"network":[60],"depths":[61],"experimented.":[62],"We":[63],"also":[64],"propose":[65],"new":[67],"model":[68,73,110],"termed":[69],"as":[70,90],"DNN-BGRU-DNN.":[71],"uses":[74],"Deep":[75],"Neural":[76],"Network":[77],"(DNN)":[78],"followed":[79],"by":[80],"Bidirectional":[82],"another":[85],"DNN.":[86],"First":[87],"DNN":[88,104],"acts":[89],"feature":[92],"processor,":[93],"BGRU":[94],"is":[95,118],"used":[96],"store":[98],"temporal":[99],"contextual":[100],"information":[101],"final":[103],"introduces":[105],"additional":[106],"non-linearity.":[107],"Our":[108],"best":[109],"achieved":[111],"13.35%":[112],"WER":[113],"TEDLIUM":[115],"dataset":[116],"which":[117],"16.66%":[120],"&":[121],"17.84%":[122],"relative":[123],"improvement":[124],"baseline":[126],"HMM-DNN":[127],"HMM-SGMM":[129],"respectively.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2018-07-10T00:00:00"}