{"id":"https://openalex.org/W2883775970","doi":"https://doi.org/10.1186/s13636-018-0128-6","title":"Advanced recurrent network-based hybrid acoustic models for low resource speech recognition","display_name":"Advanced recurrent network-based hybrid acoustic models for low resource speech recognition","publication_year":2018,"publication_date":"2018-07-17","ids":{"openalex":"https://openalex.org/W2883775970","doi":"https://doi.org/10.1186/s13636-018-0128-6","mag":"2883775970"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-018-0128-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0128-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0128-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0128-6","any_repository_has_fulltext":true},"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":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic, Engineering, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic, Engineering, Tsinghua University, Beijing, 100084, 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":true,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic, Engineering, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic, Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359533","display_name":"Weiwei Liu","orcid":"https://orcid.org/0000-0003-2188-3597"},"institutions":[{"id":"https://openalex.org/I4210162172","display_name":"Chinese People\u2019s Liberation Army 263 hospital","ror":"https://ror.org/05b51ak88","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210162172"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Wei Liu","raw_affiliation_strings":["62315 Unit, Chinese People\u2019s Liberation Army, Beijing, 100842, China","62315 Unit, Chinese People's Liberation Army, Beijing, 100842, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"62315 Unit, Chinese People\u2019s Liberation Army, Beijing, 100842, China","institution_ids":["https://openalex.org/I4210162172"]},{"raw_affiliation_string":"62315 Unit, Chinese People's Liberation Army, Beijing, 100842, China","institution_ids":["https://openalex.org/I4210162172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625092","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-1415-1195"},"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":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic, Engineering, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic, Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015797517","display_name":"Michael T. Johnson","orcid":"https://orcid.org/0000-0001-5424-4877"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael T. Johnson","raw_affiliation_strings":["Electrical and Computer Engineering, College of Engineering, University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, College of Engineering, University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100692904"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1635},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1635},"fwci":1.1198,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.83962489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2018","issue":"1","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":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":0.9994999766349792,"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":0.9991000294685364,"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":0.9255871772766113},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8309211730957031},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7998191118240356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7316957712173462},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5711086988449097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5040146708488464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49472448229789734},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45681604743003845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.377991259098053},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3677098751068115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9255871772766113},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8309211730957031},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7998191118240356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7316957712173462},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5711086988449097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5040146708488464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49472448229789734},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45681604743003845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.377991259098053},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3677098751068115},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-018-0128-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0128-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0128-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:uknowledge.uky.edu:ece_facpub-1023","is_oa":true,"landing_page_url":"https://uknowledge.uky.edu/ece_facpub/23","pdf_url":null,"source":{"id":"https://openalex.org/S4306402623","display_name":"UKnowledge (University of Kentucky)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143302722","host_organization_name":"University of Kentucky","host_organization_lineage":["https://openalex.org/I143302722"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:deb1d8f9be2e4ed2b5ffcb357447c68c","is_oa":true,"landing_page_url":"https://doaj.org/article/deb1d8f9be2e4ed2b5ffcb357447c68c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2018, Iss 1, Pp 1-15 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-018-0128-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0128-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0128-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2571867183","display_name":null,"funder_award_id":"61370034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4665116016","display_name":null,"funder_award_id":"61403224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6174077271","display_name":null,"funder_award_id":"No. 61403224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G904658873","display_name":null,"funder_award_id":"No. 61370034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2883775970.pdf","grobid_xml":"https://content.openalex.org/works/W2883775970.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W581956982","https://openalex.org/W1517386993","https://openalex.org/W1525636403","https://openalex.org/W1537895721","https://openalex.org/W1600744878","https://openalex.org/W1689711448","https://openalex.org/W1924770834","https://openalex.org/W1926954649","https://openalex.org/W1967684049","https://openalex.org/W1993721840","https://openalex.org/W1995562189","https://openalex.org/W2005708641","https://openalex.org/W2025198378","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2075449699","https://openalex.org/W2079735306","https://openalex.org/W2107878631","https://openalex.org/W2114016253","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2150907703","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2197620369","https://openalex.org/W2198724430","https://openalex.org/W2288712388","https://openalex.org/W2290318471","https://openalex.org/W2291975472","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2329068866","https://openalex.org/W2394932179","https://openalex.org/W2397450537","https://openalex.org/W2398569491","https://openalex.org/W2402146185","https://openalex.org/W2403787182","https://openalex.org/W2524611247","https://openalex.org/W2572403989","https://openalex.org/W2613006358","https://openalex.org/W2617225864","https://openalex.org/W2627210678","https://openalex.org/W2671812860","https://openalex.org/W2964084166","https://openalex.org/W2964199361","https://openalex.org/W6604896550","https://openalex.org/W6605946209"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2,105],"(RNNs)":[3],"have":[4,33,41],"shown":[5,56],"an":[6],"ability":[7],"to":[8,36,109,131,154,185],"model":[9],"temporal":[10],"dependencies.":[11],"However,":[12,60],"the":[13,61,82,133,140,145,171,198],"problem":[14,39],"of":[15,64,84,103,180],"exploding":[16],"or":[17,162],"vanishing":[18,94],"gradients":[19],"has":[20,55],"limited":[21],"their":[22,159],"application.":[23],"In":[24,79,112,169],"recent":[25],"years,":[26],"long":[27],"short-term":[28],"memory":[29],"RNNs":[30],"(LSTM":[31],"RNNs)":[32],"been":[34],"proposed":[35,150],"solve":[37],"this":[38,113],"and":[40,52,128],"achieved":[42],"excellent":[43],"results.":[44],"Bidirectional":[45],"LSTM":[46,85,104,163],"(BLSTM),":[47],"which":[48],"uses":[49],"both":[50],"preceding":[51],"following":[53],"context,":[54],"particularly":[57],"good":[58,195],"performance.":[59],"computational":[62],"requirements":[63],"BLSTM":[65,187],"approaches":[66],"are":[67,137],"quite":[68],"heavy,":[69],"even":[70],"when":[71],"implemented":[72],"efficiently":[73],"with":[74],"GPU-based":[75],"high":[76],"performance":[77],"computers.":[78],"addition,":[80,170],"because":[81],"output":[83],"units":[86,126],"is":[87,90],"bounded,":[88],"there":[89],"often":[91],"still":[92],"a":[93,120,178],"gradient":[95],"issue":[96],"over":[97,158],"multiple":[98],"layers.":[99],"The":[100,149],"large":[101],"size":[102],"makes":[106],"them":[107],"susceptible":[108],"overfitting":[110],"problems.":[111,135],"work,":[114],"we":[115,193],"combine":[116],"local":[117],"bidirectional":[118],"architecture,":[119],"new":[121,172],"recurrent":[122,125],"unit,":[123],"gated":[124],"(GRU),":[127],"residual":[129],"architectures":[130],"address":[132],"above":[134],"Experiments":[136],"conducted":[138],"on":[139],"benchmark":[141],"datasets":[142],"released":[143],"under":[144],"IARPA":[146,199],"Babel":[147,200],"Program.":[148,201],"models":[151,173],"achieve":[152,194],"3":[153],"10%":[155],"relative":[156],"improvements":[157],"corresponding":[160],"DNN":[161],"baselines":[164],"across":[165],"seven":[166],"language":[167],"collections.":[168],"accelerate":[174],"learning":[175],"speed":[176],"by":[177],"factor":[179],"more":[181],"than":[182],"1.6":[183],"compared":[184],"conventional":[186],"models.":[188],"By":[189],"using":[190],"these":[191],"approaches,":[192],"results":[196],"in":[197]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}