{"id":"https://openalex.org/W2396384435","doi":"https://doi.org/10.1109/icassp.2016.7472084","title":"Simplifying long short-term memory acoustic models for fast training and decoding","display_name":"Simplifying long short-term memory acoustic models for fast training and decoding","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2396384435","doi":"https://doi.org/10.1109/icassp.2016.7472084","mag":"2396384435"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472084","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Intern at Microsoft, Camegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Intern at Microsoft, Camegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003251887"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":25.7086,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.99516092,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9980000257492065,"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/decoding-methods","display_name":"Decoding methods","score":0.8684358596801758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8123447895050049},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6941935420036316},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5927133560180664},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.48976850509643555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46291831135749817},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46257880330085754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4512726664543152},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4381949007511139},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4321841597557068},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.42364150285720825},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4185367524623871},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08926689624786377}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8684358596801758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123447895050049},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6941935420036316},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5927133560180664},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.48976850509643555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46291831135749817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46257880330085754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4512726664543152},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4381949007511139},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4321841597557068},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.42364150285720825},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4185367524623871},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08926689624786377},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472084","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1689711448","https://openalex.org/W1788185260","https://openalex.org/W1951216520","https://openalex.org/W2005708641","https://openalex.org/W2010291496","https://openalex.org/W2048526313","https://openalex.org/W2107878631","https://openalex.org/W2119615570","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2293634267","https://openalex.org/W2294543795","https://openalex.org/W2403524927","https://openalex.org/W2963211739","https://openalex.org/W2963920996","https://openalex.org/W4285719527","https://openalex.org/W6616837769","https://openalex.org/W6629052376","https://openalex.org/W6637409405","https://openalex.org/W6640820311","https://openalex.org/W6686045668","https://openalex.org/W6696912008","https://openalex.org/W6696934422","https://openalex.org/W6713292810"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W2912831041","https://openalex.org/W2890685186","https://openalex.org/W3173606726"],"abstract_inverted_index":{"On":[0],"acoustic":[1],"modeling,":[2],"recurrent":[3,65],"neural":[4,20],"networks":[5,21],"(RNNs)":[6],"using":[7],"Long":[8],"Short-Term":[9],"Memory":[10],"(LSTM)":[11],"units":[12],"have":[13],"recently":[14],"been":[15],"shown":[16],"to":[17,77],"outperform":[18],"deep":[19],"(DNNs)":[22],"models.":[23],"This":[24],"paper":[25],"focuses":[26],"on":[27],"resolving":[28],"two":[29,54],"challenges":[30],"faced":[31],"by":[32,43,103,120],"LSTM":[33,55,101,124],"models:":[34],"high":[35],"model":[36,95,109,118],"complexity":[37],"and":[38,50,63,83,86],"poor":[39],"decoding":[40,72],"efficiency.":[41],"Motivated":[42],"our":[44],"analysis":[45],"of":[46,73,100,114,134],"the":[47,93,98,112,132],"gates":[48,59],"activation":[49],"function,":[51],"we":[52,75],"present":[53],"simplifications:":[56],"deriving":[57],"input":[58],"from":[60,67],"forget":[61],"gates,":[62],"removing":[64],"inputs":[66],"output":[68],"gates.":[69],"To":[70],"accelerate":[71],"LSTMs,":[74],"propose":[76],"apply":[78],"frame":[79,84],"skipping":[80,85],"during":[81,90,123],"training,":[82],"posterior":[87],"copying":[88],"(FSPC)":[89],"decoding.":[91,125],"In":[92],"experiments,":[94],"simplifications":[96],"reduce":[97],"size":[99],"models":[102],"26%,":[104],"resulting":[105],"in":[106],"a":[107],"simpler":[108],"structure.":[110],"Meanwhile,":[111],"application":[113],"FSPC":[115],"speeds":[116],"up":[117],"computation":[119],"2":[121],"times":[122],"All":[126],"these":[127],"improvements":[128],"are":[129],"achieved":[130],"at":[131],"cost":[133],"1%":[135],"WER":[136],"degradation.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}