{"id":"https://openalex.org/W2944697413","doi":"https://doi.org/10.1109/iscslp.2018.8706666","title":"WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition","display_name":"WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944697413","doi":"https://doi.org/10.1109/iscslp.2018.8706666","mag":"2944697413"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-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/A5063658508","display_name":"Hengguan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hengguan Huang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":["Department of Computer Science and Engineering, The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063658508"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21489777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"141","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.7668005228042603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6972454786300659},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.658379077911377},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5902091264724731},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5237988233566284},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4549848139286041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44320642948150635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3509688377380371},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2896243929862976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668005228042603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6972454786300659},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.658379077911377},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5902091264724731},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5237988233566284},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4549848139286041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44320642948150635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3509688377380371},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2896243929862976},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp.2018.8706666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.ust.hk:1783.1-95385","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=&rft.spage=&rft.aulast=Huang&rft.aufirst=&rft.atitle=WaveNet%20MH-SRU%3A%20Deep%20and%20wide%20multiple-history%20simple%20recurrent%20unit%20for%20speech%20recognition&rft.title=The%2011th%20International%20Symposium%20on%20Chinese%20Spoken%20Language%20Processing%20(ISCSLP%202018)%2C%20Taipei%2C%2026-29%20November%202018","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1493775511","https://openalex.org/W1524333225","https://openalex.org/W1895577753","https://openalex.org/W1984418626","https://openalex.org/W2045956438","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2099257174","https://openalex.org/W2101045344","https://openalex.org/W2103452139","https://openalex.org/W2107878631","https://openalex.org/W2114992418","https://openalex.org/W2133564696","https://openalex.org/W2138660131","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2194775991","https://openalex.org/W2251189452","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2746707458","https://openalex.org/W2751185861","https://openalex.org/W2949382160","https://openalex.org/W2963636093","https://openalex.org/W2964084166","https://openalex.org/W2964308564","https://openalex.org/W6607333740","https://openalex.org/W6631362777","https://openalex.org/W6679434410","https://openalex.org/W6743638068"],"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/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"Recently":[0],"the":[1,25,44,47,52,60,83,108,123,131,134,148,185,188,205],"high-order":[2,14,141,154],"multiple-history":[3],"long":[4],"short-time":[5],"memory":[6],"(MH-LSTM)":[7],"is":[8,67,89,100,104],"proposed":[9],"for":[10],"speech":[11],"recognition.":[12],"The":[13,153],"connections":[15,142,155],"to":[16,24,92,147,170],"an":[17,64,138,151],"MH-LSTM":[18,65,88],"cell":[19,66],"come":[20],"from":[21],"signals":[22],"similar":[23,213],"original":[26],"one":[27],"but":[28],"running":[29],"with":[30,77],"progressively":[31],"longer":[32],"time":[33],"lags.":[34],"Each":[35],"time-lagged":[36],"signal":[37],"keeps":[38],"a":[39,73,86,160,172],"slightly":[40],"different":[41],"history":[42,48],"of":[43,137,150,166,187,215],"input,":[45],"and":[46,79,107,140,182,199,207],"ensemble":[49],"helps":[50],"improve":[51],"model's":[53],"robustness":[54],"against":[55],"mis-labeling":[56],"or":[57],"mis-alignments":[58],"in":[59,69],"training":[61],"targets.":[62],"When":[63],"unfolded":[68],"time,":[70],"it":[71,99,103,196],"becomes":[72],"deep":[74],"neural":[75],"network":[76],"wider":[78,80,87,173],"layers":[81],"towards":[82],"inputs.":[84],"Although":[85],"more":[90,176],"resilient":[91],"noisy":[93],"data,":[94],"we":[95],"notice":[96],"that":[97,211],"when":[98],"too":[101],"wide,":[102],"easily":[105],"under-trained":[106],"increased":[109],"history/input":[110],"contexts":[111],"are":[112,120,143,156],"not":[113],"effectively":[114],"utilized.":[115],"In":[116],"this":[117],"paper,":[118],"LSTMs":[119],"replaced":[121],"by":[122,159],"faster":[124],"simple":[125],"recurrent":[126],"units":[127],"(SRUs),":[128],"which":[129,163],"remove":[130],"dependency":[132],"on":[133,180,194],"hidden":[135],"states":[136],"MH-LSTM,":[139],"instead":[144],"directly":[145],"applied":[146],"inputs":[149],"MH-SRU.":[152,191],"further":[157],"modeled":[158],"WaveNet":[161,190],"block":[162],"makes":[164],"use":[165],"dilated":[167],"causal":[168],"convolution":[169],"provide":[171],"receptive":[174],"field":[175],"effectively.":[177],"Experimental":[178],"results":[179],"NTIMIT":[181],"CHiME-2":[183],"demonstrate":[184],"effectiveness":[186],"new":[189],"For":[192],"example,":[193],"CHiME-2,":[195],"achieves":[197],"1.8%":[198],"0.6%":[200],"absolute":[201],"WER":[202],"reductions":[203],"over":[204],"SRU":[206],"MH-SRU":[208],"baseline":[209],"models":[210],"have":[212],"number":[214],"model":[216],"parameters.":[217]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}