{"id":"https://openalex.org/W2767895109","doi":"https://doi.org/10.1109/taslp.2017.2769220","title":"Optimization of RNN-Based Speech Activity Detection","display_name":"Optimization of RNN-Based Speech Activity Detection","publication_year":2017,"publication_date":"2017-11-08","ids":{"openalex":"https://openalex.org/W2767895109","doi":"https://doi.org/10.1109/taslp.2017.2769220","mag":"2767895109"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2769220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2769220","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5087187781","display_name":"Gr\u00e9gory Gelly","orcid":"https://orcid.org/0000-0003-3402-2446"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Gregory Gelly","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087187781"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":6.5418,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.97518967,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":"3","first_page":"646","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9987999796867371,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8260269165039062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8176689147949219},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6585646271705627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6143110394477844},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5954741835594177},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.5933586955070496},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5528686046600342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5360918641090393},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4494287371635437},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4387497305870056},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4360863268375397},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.385827898979187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3774263858795166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25129371881484985}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8260269165039062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176689147949219},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6585646271705627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6143110394477844},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5954741835594177},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.5933586955070496},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5528686046600342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360918641090393},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4494287371635437},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4387497305870056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4360863268375397},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.385827898979187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3774263858795166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25129371881484985},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2017.2769220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2769220","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02404747v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02404747","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2018, 26 (3), pp.646-656. ⟨10.1109/TASLP.2017.2769220⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1501620","https://openalex.org/W36345725","https://openalex.org/W950853366","https://openalex.org/W1408639475","https://openalex.org/W1522301498","https://openalex.org/W1566399673","https://openalex.org/W1566422088","https://openalex.org/W1815076433","https://openalex.org/W1985242443","https://openalex.org/W1999127798","https://openalex.org/W1999454387","https://openalex.org/W2038587377","https://openalex.org/W2048497537","https://openalex.org/W2064675550","https://openalex.org/W2068702980","https://openalex.org/W2073693905","https://openalex.org/W2108289863","https://openalex.org/W2108563286","https://openalex.org/W2109364787","https://openalex.org/W2110485445","https://openalex.org/W2115717467","https://openalex.org/W2117824074","https://openalex.org/W2119535101","https://openalex.org/W2126693545","https://openalex.org/W2131774270","https://openalex.org/W2134299061","https://openalex.org/W2143612262","https://openalex.org/W2143908786","https://openalex.org/W2144499799","https://openalex.org/W2148154194","https://openalex.org/W2150355110","https://openalex.org/W2169245194","https://openalex.org/W2240641835","https://openalex.org/W2401364490","https://openalex.org/W2403186097","https://openalex.org/W2403657120","https://openalex.org/W2405388169","https://openalex.org/W2406226915","https://openalex.org/W2406262283","https://openalex.org/W2408468399","https://openalex.org/W2587899496","https://openalex.org/W2964121744","https://openalex.org/W3007258144","https://openalex.org/W4254816979","https://openalex.org/W4285719527","https://openalex.org/W6601464659","https://openalex.org/W6628131027","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6713037448","https://openalex.org/W6713511519","https://openalex.org/W6713752823","https://openalex.org/W6713986472"],"related_works":["https://openalex.org/W2807901368","https://openalex.org/W2158491338","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2539884462","https://openalex.org/W2149402184"],"abstract_inverted_index":{"Speech":[0,164],"activity":[1],"detection":[2,64],"(SAD)":[3],"is":[4,124],"an":[5,21],"essential":[6],"component":[7],"of":[8,72,79,89,140],"automatic":[9],"speech":[10,75],"recognition":[11,165],"systems":[12],"impacting":[13],"the":[14,43,47,58,62,68,137,141,150,170,179,185,191,195,199],"overall":[15],"system":[16,35],"performance.":[17],"This":[18,31],"paper":[19],"investigates":[20],"optimization":[22,83,118,123,181],"process":[23,32],"for":[24,40,55,116,136],"recurrent":[25],"neural":[26,142],"network":[27,100,108],"(RNN)":[28],"based":[29],"SAD.":[30],"optimizes":[33],"all":[34,175,190],"parameters":[36],"including":[37],"those":[38],"used":[39,125],"feature":[41,128],"extraction,":[42],"NN":[44],"weights,":[45],"and":[46,67,82,103,112,130,160,177,188],"back-end":[48],"parameters.":[49],"Three":[50,87],"cost":[51,65],"functions":[52],"are":[53,85,91,147,167],"considered":[54],"SAD":[56,145,153,186,193],"optimization:":[57],"frame":[59],"error":[60,70],"rate,":[61],"NIST":[63,151],"function,":[66],"word":[69],"rate":[71],"a":[73,93,104],"downstream":[74],"recognizer.":[76],"Different":[77],"types":[78,88],"RNN":[80],"models":[81],"methods":[84,194],"investigated.":[86],"RNNs":[90],"compared:":[92],"basic":[94],"RNN,":[95],"long":[96],"short-term":[97],"memory":[98],"(LSTM)":[99],"with":[101],"peepholes,":[102],"coordinated-gate":[105],"LSTM":[106],"(CG-LSTM)":[107],"introduced":[109],"by":[110],"Gelly":[111],"Gauvain.":[113],"Well":[114],"suited":[115],"nondifferentiable":[117],"problems,":[119],"quantum-behaved":[120],"particle":[121],"swarm":[122],"to":[126],"optimize":[127],"extraction":[129],"posterior":[131],"smoothing,":[132],"as":[133,135,156,158],"well":[134,157],"initial":[138],"training":[139],"networks.":[143],"Experimental":[144],"results":[146,166],"reported":[148,168],"on":[149,169],"2015":[152],"evaluation":[154],"data":[155],"REPERE":[159],"AMI":[161],"meeting":[162],"corpora.":[163],"OpenKWS'13":[171],"test":[172],"data.":[173],"For":[174],"tasks":[176],"conditions,":[178],"proposed":[180],"method":[182],"significantly":[183],"improves":[184],"performance":[187],"among":[189],"tested":[192],"CG-LSTM":[196],"model":[197],"gives":[198],"best":[200],"results.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-23T07:41:27.035349","created_date":"2025-10-10T00:00:00"}