{"id":"https://openalex.org/W1886418050","doi":"https://doi.org/10.1109/icassp.2015.7178842","title":"Improving long short-term memory networks using maxout units for large vocabulary speech recognition","display_name":"Improving long short-term memory networks using maxout units for large vocabulary speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1886418050","doi":"https://doi.org/10.1109/icassp.2015.7178842","mag":"1886418050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178842","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":"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/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"],"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"],"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":4.3143,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94565726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":null,"first_page":"4600","last_page":"4604"},"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8579210638999939},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.737932562828064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7293593883514404},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6151217222213745},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.612729549407959},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5514900088310242},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5143802762031555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5050538182258606},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4603441059589386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32530471682548523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06562760472297668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579210638999939},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.737932562828064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7293593883514404},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6151217222213745},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.612729549407959},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5514900088310242},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5143802762031555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5050538182258606},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4603441059589386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32530471682548523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06562760472297668},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178842","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1815076433","https://openalex.org/W1968419113","https://openalex.org/W1981706894","https://openalex.org/W1988745938","https://openalex.org/W1993882792","https://openalex.org/W1995840259","https://openalex.org/W2026369565","https://openalex.org/W2035424729","https://openalex.org/W2057653135","https://openalex.org/W2062227835","https://openalex.org/W2064675550","https://openalex.org/W2087402357","https://openalex.org/W2089917322","https://openalex.org/W2107878631","https://openalex.org/W2117951582","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2156387975","https://openalex.org/W2160815625","https://openalex.org/W2188736355","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2403787182","https://openalex.org/W4285719527","https://openalex.org/W6629930100","https://openalex.org/W6631362777","https://openalex.org/W6638545294","https://openalex.org/W6682889407","https://openalex.org/W6696761078","https://openalex.org/W6696934422","https://openalex.org/W6696982659","https://openalex.org/W6697318756","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-tem":[1],"memory":[2],"(LSTM)":[3],"recurrent":[4],"neural":[5,49],"networks":[6,67],"have":[7,42],"been":[8],"shown":[9],"to":[10,32,46],"give":[11],"state-of-the-art":[12],"performance":[13,23,107],"on":[14,77,89],"many":[15],"speech":[16,96],"recognition":[17,97],"tasks.":[18],"To":[19],"achieve":[20],"a":[21,90],"further":[22,115],"improvement,":[24],"in":[25,64],"this":[26],"paper,":[27],"maxout":[28,69,119],"units":[29,41,61],"are":[30],"proposed":[31,87],"be":[33,114],"integrated":[34],"with":[35,68,80],"the":[36,58,65,73,86,106,118],"LSTM":[37,66,74,109],"cells,":[38],"considering":[39],"those":[40],"brought":[43],"significant":[44],"improvements":[45],"deep":[47],"feed-forward":[48],"networks.":[50],"A":[51],"novel":[52],"architecture":[53],"was":[54],"constructed":[55],"by":[56],"replacing":[57],"input":[59],"activation":[60],"(generally":[62],"tanh)":[63],"units.":[70,120],"We":[71],"implemented":[72],"network":[75],"training":[76],"multi-GPU":[78],"devices":[79],"truncated":[81],"BPTT,":[82],"and":[83],"empirically":[84],"evaluated":[85],"designs":[88],"large":[91],"vocabulary":[92],"Mandarin":[93],"conversational":[94],"telephone":[95],"task.":[98],"The":[99],"experimental":[100],"results":[101],"support":[102],"our":[103],"claim":[104],"that":[105],"of":[108],"based":[110],"acoustic":[111],"models":[112],"can":[113],"improved":[116],"using":[117]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}