{"id":"https://openalex.org/W2406799407","doi":"https://doi.org/10.1109/icassp.2016.7472718","title":"Exploiting LSTM structure in deep neural networks for speech recognition","display_name":"Exploiting LSTM structure in deep neural networks for speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2406799407","doi":"https://doi.org/10.1109/icassp.2016.7472718","mag":"2406799407"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5051747323","display_name":"Tianxing He","orcid":"https://orcid.org/0009-0008-6383-0307"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianxing He","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft Research, Redmond"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051747323"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.88719696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5445","last_page":"5449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8226763010025024},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7014350891113281},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6693817377090454},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6533170342445374},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5863736867904663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790498852729797},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5592930912971497},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5533490180969238},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5050469040870667},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49615272879600525},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47569072246551514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4607274532318115},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4577372074127197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43339380621910095},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4213674068450928},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4192710518836975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3532094359397888},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06952986121177673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226763010025024},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7014350891113281},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6693817377090454},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6533170342445374},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5863736867904663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790498852729797},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5592930912971497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5533490180969238},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5050469040870667},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49615272879600525},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47569072246551514},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4607274532318115},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4577372074127197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43339380621910095},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4213674068450928},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4192710518836975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3532094359397888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06952986121177673},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/icassp.2016.7472718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1513982904","https://openalex.org/W1533861849","https://openalex.org/W1899504021","https://openalex.org/W1916589227","https://openalex.org/W2005708641","https://openalex.org/W2062227835","https://openalex.org/W2064675550","https://openalex.org/W2130942839","https://openalex.org/W2136922672","https://openalex.org/W2160306971","https://openalex.org/W2329068866","https://openalex.org/W2397424575","https://openalex.org/W2402268235","https://openalex.org/W2407022425","https://openalex.org/W2962965465","https://openalex.org/W3038058348","https://openalex.org/W6631636882","https://openalex.org/W6631943919","https://openalex.org/W6638205174","https://openalex.org/W6640218462","https://openalex.org/W6679436768","https://openalex.org/W6701770434","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4288108708","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W4387163678","https://openalex.org/W2973430807","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W4385280324","https://openalex.org/W2098529290"],"abstract_inverted_index":{"The":[0],"CD-DNN-HMM":[1],"system":[2,7],"has":[3,57],"became":[4],"the":[5,31,49,80,112],"state-of-art":[6],"for":[8],"large":[9],"vocabulary":[10],"continuous":[11],"speech":[12],"recognition":[13],"(LVCSR)":[14],"tasks,":[15],"in":[16],"which":[17,56,83],"deep":[18,38],"neural":[19,63],"networks":[20],"(DNN)":[21],"plays":[22],"a":[23,76],"key":[24],"role.":[25],"However,":[26],"DNN":[27],"training":[28,36],"suffers":[29],"from":[30],"vanishing":[32],"gradient":[33],"problem,":[34],"limiting":[35],"of":[37,79],"models.":[39],"In":[40,88],"this":[41,45],"work,":[42],"we":[43,74,84],"address":[44],"problem":[46],"by":[47],"incorporating":[48],"successful":[50],"long-short":[51],"term":[52,69],"memory":[53],"(LSTM)":[54],"structure,":[55],"been":[58],"proposed":[59,96],"to":[60,66],"help":[61],"recurrent":[62],"network":[64],"(RNN)":[65],"remember":[67],"long":[68],"dependencies,":[70],"into":[71],"DNN.":[72],"Also,":[73],"propose":[75],"generalized":[77],"formulation":[78],"LSTM":[81],"block,":[82],"name":[85],"general":[86],"LSTM(GLSTM).":[87],"our":[89,95],"experiments,":[90],"it":[91],"is":[92],"shown":[93],"that":[94],"(G)LSTM-DNN":[97],"scales":[98],"well":[99],"with":[100],"more":[101],"layers,":[102],"and":[103],"achieves":[104],"8.2%":[105],"relative":[106],"word":[107],"error":[108],"rate":[109],"reduction":[110],"on":[111],"2000-hour":[113],"Switchboard":[114],"data":[115],"set.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}