{"id":"https://openalex.org/W2613006358","doi":"https://doi.org/10.1109/iscslp.2016.7918456","title":"Gated recurrent units based hybrid acoustic models for robust speech recognition","display_name":"Gated recurrent units based hybrid acoustic models for robust speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2613006358","doi":"https://doi.org/10.1109/iscslp.2016.7918456","mag":"2613006358"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5049139590","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0003-3797-256X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Kang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7765,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76665438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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":0.9984999895095825,"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/overfitting","display_name":"Overfitting","score":0.9119086265563965},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8670331239700317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893890738487244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544570803642273},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.529040515422821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5029744505882263},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.49462029337882996},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4709908366203308},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44577646255493164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4154731035232544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2685384750366211},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08385661244392395}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9119086265563965},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8670331239700317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893890738487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544570803642273},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.529040515422821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5029744505882263},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.49462029337882996},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4709908366203308},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44577646255493164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4154731035232544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2685384750366211},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08385661244392395},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W581956982","https://openalex.org/W1586532344","https://openalex.org/W1600744878","https://openalex.org/W1689711448","https://openalex.org/W1924770834","https://openalex.org/W2005708641","https://openalex.org/W2009934439","https://openalex.org/W2057826000","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2075449699","https://openalex.org/W2107878631","https://openalex.org/W2114863652","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2193413348","https://openalex.org/W2290318471","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2403787182","https://openalex.org/W2755891984","https://openalex.org/W2964199361","https://openalex.org/W4302114989"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2],"(RNNs)":[3],"have":[4,33,41],"shown":[5],"an":[6,91],"ability":[7],"to":[8,36,98,133,214],"model":[9,118],"temporal":[10],"dependencies.":[11],"However":[12],"the":[13,48,68,108,111,125,128,139,160,173,192,197],"problem":[14],"of":[15,47,51,70,110,127,142],"exploding":[16],"or":[17],"vanishing":[18,80,143],"gradients":[19,144],"has":[20],"limited":[21],"their":[22],"application.":[23],"In":[24,65,86,103],"recent":[25],"years,":[26],"long":[27],"short-term":[28],"memory":[29],"RNNs":[30],"(LSTM":[31],"RNNs)":[32],"been":[34],"proposed":[35],"solve":[37,99],"this":[38,87,117,170],"problem,":[39],"and":[40,158,162,166],"achieved":[42],"excellent":[43],"results.":[44],"However,":[45],"because":[46,67],"large":[49],"size":[50,109],"LSTM":[52,71,106,165],"RNNs,":[53],"they":[54],"more":[55,120],"easily":[56,121],"suffer":[57],"from":[58],"overfitting,":[59],"especially":[60],"for":[61],"low":[62,178],"resource":[63,179],"tasks.":[64],"addition,":[66],"output":[69,126],"units":[72,96],"is":[73,76,114,130],"bounded,":[74,135],"there":[75],"often":[77],"still":[78],"a":[79,176,204,215],"gradient":[81],"issue":[82],"over":[83],"multiple":[84,146],"layers.":[85,147],"work,":[88],"we":[89],"evaluate":[90,169],"architecture":[92,171,187],"called":[93],"gated":[94],"recurrent":[95],"(GRU)":[97],"these":[100],"two":[101],"problems.":[102],"comparison":[104],"with":[105,203],"RNN,":[107],"GRU":[112,129],"network":[113],"smaller,":[115],"so":[116],"can":[119],"avoid":[122],"overfitting.":[123],"Furthermore,":[124],"not":[131],"constrained":[132],"be":[134],"which":[136],"helps":[137],"alleviate":[138],"negative":[140],"impact":[141],"across":[145],"We":[148,168],"propose":[149],"using":[150],"deep":[151],"bidirectional":[152,198],"GRUs":[153],"as":[154],"hybrid":[155],"acoustic":[156],"models":[157],"compare":[159],"similarities":[161],"differences":[163],"between":[164],"GRU.":[167],"on":[172],"CHIME2":[174],"dataset,":[175],"robust":[177],"speech":[180],"recognition":[181],"task.":[182],"Results":[183],"demonstrate":[184],"that":[185],"our":[186],"outperforms":[188],"LSTM,":[189],"relatively":[190],"decreasing":[191],"WER":[193,211],"about":[194],"6%":[195],"in":[196],"case":[199],"and,":[200],"when":[201],"combined":[202],"baseline":[205,217],"GMM":[206],"system,":[207],"achieves":[208],"1.1%":[209],"absolute":[210],"reduction":[212],"comparing":[213],"strong":[216],"mixing":[218],"system.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}