{"id":"https://openalex.org/W2612230706","doi":"https://doi.org/10.1109/iscslp.2016.7918375","title":"Deep long short-term memory networks for speech recognition","display_name":"Deep long short-term memory networks for speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2612230706","doi":"https://doi.org/10.1109/iscslp.2016.7918375","mag":"2612230706"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918375","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015832472","display_name":"Alim Misbullah","orcid":"https://orcid.org/0000-0002-0132-5961"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Alim Misbullah","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8092961311340332},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7966374158859253},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.6440948247909546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6413999795913696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6175817847251892},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5927556753158569},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5095062851905823},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.48417335748672485},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47940823435783386},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43853017687797546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3460477888584137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092961311340332},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7966374158859253},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.6440948247909546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413999795913696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6175817847251892},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5927556753158569},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5095062851905823},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.48417335748672485},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47940823435783386},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43853017687797546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3460477888584137},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918375","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1513982904","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1600744878","https://openalex.org/W1810943226","https://openalex.org/W1815076433","https://openalex.org/W1993882792","https://openalex.org/W2015631279","https://openalex.org/W2019991208","https://openalex.org/W2052250648","https://openalex.org/W2057653135","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2119615570","https://openalex.org/W2136016850","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2170942820","https://openalex.org/W2242047860","https://openalex.org/W2289394825","https://openalex.org/W2293634267","https://openalex.org/W2329068866","https://openalex.org/W2394932179","https://openalex.org/W2403787182","https://openalex.org/W2964084166","https://openalex.org/W2964335273","https://openalex.org/W6607333740","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6696934422","https://openalex.org/W6711962127","https://openalex.org/W6713412349"],"related_works":["https://openalex.org/W3008584592","https://openalex.org/W2912153778","https://openalex.org/W4288108708","https://openalex.org/W4387163678","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W3173606726"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"has":[2],"been":[3],"significantly":[4],"improved":[5],"by":[6,106],"applying":[7],"acoustic":[8],"models":[9,169],"based":[10,61],"on":[11,62,141],"deep":[12,40,101,136],"neural":[13],"network":[14],"which":[15,103],"could":[16],"be":[17],"realized":[18],"as":[19],"the":[20,25,36,50,88,112,123,128,152,166],"feedforward":[21,119],"NN":[22,27],"(FNN)":[23],"or":[24],"recurrent":[26],"(RNN).":[28],"In":[29],"general,":[30],"FNN":[31,90,158,162],"is":[32,46,67,104],"feasible":[33],"to":[34,48],"project":[35],"observations":[37],"onto":[38],"a":[39,54,73,80,100,135],"invariant":[41],"feature":[42],"space":[43],"while":[44],"RNN":[45,60,92],"beneficial":[47],"capture":[49],"temporal":[51,85,124],"information":[52],"in":[53,93,134],"sequential":[55],"data":[56],"for":[57,83,170],"speech":[58,172],"recognition.":[59,173],"long":[63,74,129],"short-term":[64],"memory":[65],"(LSTM)":[66],"capable":[68],"of":[69,114,131,154],"storing":[70],"inputs":[71,133],"over":[72],"time":[75],"period":[76],"and":[77,91,109,117,126,148,163,165],"thus":[78],"exploiting":[79],"self-learned":[81],"mechanism":[82],"long-range":[84],"context.":[86],"Considering":[87],"complimentary":[89],"their":[94],"modeling":[95],"capabilities,":[96],"this":[97],"paper":[98],"presents":[99],"model":[102,156],"constructed":[105],"stacking":[107],"LSTM":[108,115,164],"FNN.":[110],"Through":[111],"cascade":[113],"cells":[116],"fully-connected":[118],"units,":[120],"we":[121],"explore":[122],"patterns":[125],"summarize":[127],"history":[130],"previous":[132],"learning":[137],"machine.":[138],"The":[139],"experiments":[140],"3":[142],"<sup":[143],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">rd</sup>":[145],"CHiME":[146],"challenge":[147],"Aurora-4":[149],"show":[150],"that":[151],"stacks":[153],"hybrid":[155,168],"with":[157],"post-processor":[159],"outperform":[160],"stand-alone":[161],"other":[167],"robust":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}