{"id":"https://openalex.org/W2587529061","doi":"https://doi.org/10.1109/slt.2016.7846306","title":"Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting","display_name":"Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2587529061","doi":"https://doi.org/10.1109/slt.2016.7846306","mag":"2587529061"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.02411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ming Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon.com, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Anirudh Raju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":["Amazon.com, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"George Tucker","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":"George Tucker","raw_affiliation_strings":["Google Brain, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sankaran Panchapagesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankaran Panchapagesan","raw_affiliation_strings":["Amazon.com, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gengshen Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gengshen Fu","raw_affiliation_strings":["Amazon.com, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arindam Mandal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arindam Mandal","raw_affiliation_strings":["Amazon.com, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Spyros Matsoukas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":["Amazon.com, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nikko Strom","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikko Strom","raw_affiliation_strings":["Amazon.com, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shiv Vitaladevuni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiv Vitaladevuni","raw_affiliation_strings":["Amazon.com, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3316,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.97963792,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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/keyword-spotting","display_name":"Keyword spotting","score":0.7228000164031982},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6710000038146973},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5493999719619751},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5462999939918518},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4602000117301941},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42239999771118164},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41670000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487000226974487},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7228000164031982},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479000210762024},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.31679999828338623},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2016.7846306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.02411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.02411","pdf_url":"https://arxiv.org/pdf/1705.02411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.02411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.02411","pdf_url":"https://arxiv.org/pdf/1705.02411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1553469512","https://openalex.org/W1923404803","https://openalex.org/W1983205135","https://openalex.org/W1999121090","https://openalex.org/W2000654171","https://openalex.org/W2021167964","https://openalex.org/W2034940213","https://openalex.org/W2064675550","https://openalex.org/W2074671152","https://openalex.org/W2101346879","https://openalex.org/W2122797512","https://openalex.org/W2127141656","https://openalex.org/W2293968535","https://openalex.org/W2409050142","https://openalex.org/W2507319753","https://openalex.org/W2507580616","https://openalex.org/W6604666349","https://openalex.org/W6629510986","https://openalex.org/W6631319189","https://openalex.org/W6683369307","https://openalex.org/W6696934422","https://openalex.org/W6697212960","https://openalex.org/W6713453343","https://openalex.org/W6713835734","https://openalex.org/W6714171909"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,37,70,106],"max-pooling":[3,27,67,82,100],"based":[4,45],"loss":[5,28,39,65,68,72,83,95,101],"function":[6],"for":[7,14],"training":[8,29],"Long":[9],"Short-Term":[10],"Memory":[11],"(LSTM)":[12],"networks":[13],"small-footprint":[15],"keyword":[16,52],"spotting":[17,53],"(KWS),":[18],"with":[19,36,86,105],"low":[20],"CPU,":[21],"memory,":[22],"and":[23],"latency":[24],"requirements.":[25],"The":[26],"can":[30],"be":[31],"further":[32],"guided":[33],"by":[34],"initializing":[35],"cross-entropy":[38,64,71,94,107],"trained":[40,62,73,84,96,102],"network.":[41],"A":[42],"posterior":[43],"smoothing":[44],"evaluation":[46],"approach":[47],"is":[48],"employed":[49],"to":[50,93,120],"measure":[51],"performance.":[54],"Our":[55],"experimental":[56],"results":[57],"show":[58],"that":[59],"LSTM":[60,85,103],"models":[61],"using":[63],"or":[66],"outperform":[69],"baseline":[74,121],"feed-forward":[75,122],"Deep":[76],"Neural":[77],"Network":[78],"(DNN).":[79],"In":[80],"addition,":[81],"randomly":[87],"initialized":[88,104],"network":[89,109],"performs":[90],"better":[91],"compared":[92,119],"LSTM.":[97],"Finally,":[98],"the":[99,111,127],"pre-trained":[108],"shows":[110],"best":[112],"performance,":[113],"which":[114],"yields":[115],"67:6%":[116],"relative":[117],"reduction":[118],"DNN":[123],"in":[124],"Area":[125],"Under":[126],"Curve":[128],"(AUC)":[129],"measure.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2017-02-17T00:00:00"}