{"id":"https://openalex.org/W2787110826","doi":"https://doi.org/10.1109/asru.2017.8268930","title":"Gated convolutional networks based hybrid acoustic models for low resource speech recognition","display_name":"Gated convolutional networks based hybrid acoustic models for low resource speech recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787110826","doi":"https://doi.org/10.1109/asru.2017.8268930","mag":"2787110826"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268930","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 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":"2017 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/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":0.6921,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76122998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"157","last_page":"164"},"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":0.9987000226974487,"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":0.9962000250816345,"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":0.8505215048789978},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7351329326629639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6403167843818665},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6176344752311707},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5769830942153931},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5292462706565857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5211929678916931},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4494459629058838},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4343867897987366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3579818904399872},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3428875505924225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2839238941669464},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20106825232505798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8505215048789978},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7351329326629639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6403167843818665},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6176344752311707},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5769830942153931},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5292462706565857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211929678916931},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4494459629058838},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4343867897987366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3579818904399872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3428875505924225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2839238941669464},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20106825232505798},{"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":1,"locations":[{"id":"doi:10.1109/asru.2017.8268930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268930","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 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":"2017 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/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1995562189","https://openalex.org/W2005708641","https://openalex.org/W2025198378","https://openalex.org/W2031804986","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2117671523","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2187089797","https://openalex.org/W2198724430","https://openalex.org/W2208299922","https://openalex.org/W2271177914","https://openalex.org/W2288712388","https://openalex.org/W2290318471","https://openalex.org/W2291975472","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2402146185","https://openalex.org/W2403787182","https://openalex.org/W2508023766","https://openalex.org/W2519224033","https://openalex.org/W2524611247","https://openalex.org/W2533523411","https://openalex.org/W2671812860","https://openalex.org/W2963970792","https://openalex.org/W2964199361","https://openalex.org/W6631362777","https://openalex.org/W6696982659","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2964954556","https://openalex.org/W2921005841"],"abstract_inverted_index":{"In":[0,53,70,117,192],"acoustic":[1,85,105],"modeling":[2],"for":[3,44,51],"large":[4],"vocabulary":[5],"speech":[6,129],"recognition,":[7],"recurrent":[8],"neural":[9,38],"networks":[10,39,135,169],"(RNN)":[11],"have":[12],"shown":[13],"great":[14],"abilities":[15],"to":[16,65,83,103,109,126,139,146,209],"model":[17,66],"temporal":[18],"dependencies.":[19,69],"However,":[20],"the":[21,35,88,153,164,166,172,177,183,189,194,198,212],"performance":[22],"of":[23,112,157,211],"RNN":[24,45],"is":[25,46,79,99],"not":[26],"prominent":[27],"in":[28],"resource":[29,128,159],"limited":[30],"tasks,":[31],"even":[32],"worse":[33],"than":[34,49,203],"traditional":[36],"feedforward":[37],"(FNN).":[40],"Furthermore,":[41],"training":[42],"time":[43],"much":[47],"more":[48,202],"that":[50,75,95,210],"FNN.":[52],"recent":[54],"years,":[55],"some":[56],"novel":[57],"models":[58,185,196],"are":[59,150],"provided.":[60],"They":[61],"use":[62,136],"non-recurrent":[63],"architectures":[64,138],"long":[67],"term":[68],"these":[71,114],"architectures,":[72],"they":[73],"show":[74],"using":[76,96],"gate":[77,145],"mechanism":[78],"an":[80],"effective":[81],"method":[82,102],"construct":[84],"models.":[86,191,217],"On":[87],"other":[89],"hand,":[90],"it":[91],"has":[92],"been":[93],"proved":[94],"convolution":[97],"operation":[98],"a":[100,122,144,155],"good":[101],"learn":[104,140],"features.":[106],"We":[107],"hope":[108],"take":[110],"advantages":[111],"both":[113],"two":[115],"methods.":[116],"this":[118],"paper":[119],"we":[120],"present":[121],"gated":[123,133,167],"convolutional":[124,134,137,168],"approach":[125],"low":[127,158],"recognition":[130],"tasks.":[131],"The":[132],"input":[141],"features":[142],"and":[143,186,205,215],"control":[147],"information.":[148],"Experiments":[149],"conducted":[151],"on":[152],"OpenKWS,":[154],"series":[156],"keyword":[160],"search":[161],"evaluations.":[162],"From":[163],"results,":[165],"relatively":[170],"decrease":[171],"WER":[173],"about":[174],"6%":[175],"over":[176,182,188],"baseline":[178,213],"LSTM":[179,214],"models,":[180],"5%":[181],"DNN":[184],"3%":[187],"BLSTM":[190,216],"addition,":[193],"new":[195],"accelerate":[197],"learning":[199],"speed":[200],"by":[201],"1.8":[204],"3.2":[206],"times":[207],"compared":[208]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}