{"id":"https://openalex.org/W2963991999","doi":"https://doi.org/10.1109/icassp.2016.7472821","title":"Learning compact recurrent neural networks","display_name":"Learning compact recurrent neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2963991999","doi":"https://doi.org/10.1109/icassp.2016.7472821","mag":"2963991999"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472821","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":"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/A5089287882","display_name":"Zhiyun Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyun Lu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058073838","display_name":"Vikas Sindhwani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikas Sindhwani","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089287882"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":9.30193701,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.9905095,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"5960","last_page":"5964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.9452601671218872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324440121650696},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.6534995436668396},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6278694272041321},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6112315058708191},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5486330986022949},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5262731313705444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44269251823425293},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4386327862739563},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4305822253227234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40696945786476135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36936551332473755},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07544130086898804}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.9452601671218872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324440121650696},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.6534995436668396},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6278694272041321},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6112315058708191},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5486330986022949},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5262731313705444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44269251823425293},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4386327862739563},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4305822253227234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40696945786476135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36936551332473755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07544130086898804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472821","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":29,"referenced_works":["https://openalex.org/W21639112","https://openalex.org/W581956982","https://openalex.org/W1594170634","https://openalex.org/W1600744878","https://openalex.org/W1689711448","https://openalex.org/W1821462560","https://openalex.org/W1841592590","https://openalex.org/W2064675550","https://openalex.org/W2100649405","https://openalex.org/W2136848157","https://openalex.org/W2168231600","https://openalex.org/W2172166488","https://openalex.org/W2182629226","https://openalex.org/W2293634267","https://openalex.org/W2294543795","https://openalex.org/W2400505028","https://openalex.org/W2949964376","https://openalex.org/W2952432176","https://openalex.org/W2963374099","https://openalex.org/W2979307260","https://openalex.org/W6635557998","https://openalex.org/W6637409405","https://openalex.org/W6638523607","https://openalex.org/W6638783484","https://openalex.org/W6684859321","https://openalex.org/W6686067075","https://openalex.org/W6696912008","https://openalex.org/W6696934422","https://openalex.org/W6712772800"],"related_works":["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","https://openalex.org/W4285503423"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2],"(RNNs),":[3],"including":[4],"long":[5],"short-term":[6],"memory":[7,36],"(LSTM)":[8],"RNNs,":[9],"have":[10],"produced":[11],"state-of-the-art":[12],"results":[13],"on":[14,32,91,119],"a":[15,105,111,120],"variety":[16],"of":[17,79,104,114],"speech":[18],"recognition":[19],"tasks.":[20],"However,":[21],"these":[22],"models":[23],"are":[24],"often":[25],"too":[26],"large":[27],"in":[28,65,83,117],"size":[29],"for":[30,46],"deployment":[31],"mobile":[33],"devices":[34],"with":[35],"and":[37,50,55,87],"latency":[38],"constraints.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"study":[44],"mechanisms":[45],"learning":[47],"compact":[48],"RNNs":[49],"LSTMs":[51],"via":[52],"low-rank":[53,89],"factorizations":[54],"parameter":[56],"sharing":[57],"schemes.":[58],"Our":[59],"goal":[60],"is":[61,95],"to":[62,97],"investigate":[63],"redundancies":[64],"recurrent":[66],"architectures":[67],"where":[68],"compression":[69],"can":[70],"be":[71,98],"admitted":[72],"without":[73],"losing":[74],"performance.":[75],"A":[76],"hybrid":[77],"strategy":[78],"using":[80],"structured":[81],"matrices":[82],"the":[84,92,102],"bottom":[85],"layers":[86,94],"shared":[88],"factors":[90],"top":[93],"found":[96],"particularly":[99],"effective,":[100],"reducing":[101],"parameters":[103],"standard":[106],"LSTM":[107],"by":[108],"75%,":[109],"at":[110],"small":[112],"cost":[113],"0.3%":[115],"increase":[116],"WER,":[118],"2,000-hr":[121],"English":[122],"Voice":[123],"Search":[124],"task.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}