{"id":"https://openalex.org/W2119615570","doi":"https://doi.org/10.1109/icassp.2015.7178826","title":"Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition","display_name":"Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2119615570","doi":"https://doi.org/10.1109/icassp.2015.7178826","mag":"2119615570"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing","Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing","Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081173423"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":29.3818,"has_fulltext":false,"cited_by_count":334,"citation_normalized_percentile":{"value":0.99656897,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4520","last_page":"4524"},"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":0.9986000061035156,"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":0.860257089138031},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7541691064834595},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.6958680748939514},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6914368867874146},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6672476530075073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6497863531112671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6401001811027527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5738407373428345},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5514331459999084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47282350063323975},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46800389885902405},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4401002824306488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313421905040741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.860257089138031},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7541691064834595},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.6958680748939514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6914368867874146},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6672476530075073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6497863531112671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6401001811027527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738407373428345},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5514331459999084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47282350063323975},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46800389885902405},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4401002824306488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313421905040741},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W299739017","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1815076433","https://openalex.org/W1886418050","https://openalex.org/W1889624880","https://openalex.org/W1981706894","https://openalex.org/W1988745938","https://openalex.org/W1993882792","https://openalex.org/W1995840259","https://openalex.org/W2005708641","https://openalex.org/W2026369565","https://openalex.org/W2035424729","https://openalex.org/W2057653135","https://openalex.org/W2064675550","https://openalex.org/W2075925017","https://openalex.org/W2087402357","https://openalex.org/W2107878631","https://openalex.org/W2122585011","https://openalex.org/W2127141656","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2188736355","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2294797155","https://openalex.org/W2394932179","https://openalex.org/W2403787182","https://openalex.org/W2406392101","https://openalex.org/W2949190276","https://openalex.org/W2964335273","https://openalex.org/W4231109964","https://openalex.org/W4285719527","https://openalex.org/W6629930100","https://openalex.org/W6631362777","https://openalex.org/W6631545277","https://openalex.org/W6638545294","https://openalex.org/W6639497327","https://openalex.org/W6696843773","https://openalex.org/W6696934422","https://openalex.org/W6696982659","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":{"Long":[0],"short-term":[1],"memory":[2],"(LSTM)":[3],"based":[4],"acoustic":[5],"modeling":[6],"methods":[7],"have":[8],"recently":[9],"been":[10],"shown":[11],"to":[12,44,83],"give":[13],"state-of-the-art":[14,111],"performance":[15,25,112],"on":[16,32,56,72,113],"some":[17],"speech":[18,78],"recognition":[19,79],"tasks.":[20],"To":[21],"achieve":[22],"a":[23,49,73],"further":[24],"improvement,":[26],"in":[27],"this":[28,114],"research,":[29],"deep":[30,38,58,64,101],"extensions":[31],"LSTM":[33,65,90,102],"are":[34,67],"investigated":[35],"considering":[36],"that":[37,99],"hierarchical":[39],"model":[40],"has":[41],"turned":[42],"out":[43],"be":[45],"more":[46],"efficient":[47],"than":[48],"shallow":[50],"one.":[51],"Motivated":[52],"by":[53],"previous":[54],"research":[55],"constructing":[57],"recurrent":[59],"neural":[60],"networks":[61,91,103],"(RNNs),":[62],"alternative":[63],"architectures":[66],"proposed":[68],"and":[69,94,108],"empirically":[70],"evaluated":[71],"large":[74],"vocabulary":[75],"conversational":[76],"telephone":[77],"task.":[80,115],"Meanwhile,":[81],"regarding":[82],"multi-GPU":[84],"devices,":[85],"the":[86,100,106,110],"training":[87],"process":[88],"for":[89],"is":[92],"introduced":[93],"discussed.":[95],"Experimental":[96],"results":[97],"demonstrate":[98],"benefit":[104],"from":[105],"depth":[107],"yield":[109]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":51},{"year":2020,"cited_by_count":60},{"year":2019,"cited_by_count":40},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":5}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}