{"id":"https://openalex.org/W2902572630","doi":"https://doi.org/10.1109/icpr.2018.8546063","title":"Recurrent Neural Network Based Small-footprint Wake-up-word Speech Recognition System with a Score Calibration Method","display_name":"Recurrent Neural Network Based Small-footprint Wake-up-word Speech Recognition System with a Score Calibration Method","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2902572630","doi":"https://doi.org/10.1109/icpr.2018.8546063","mag":"2902572630"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8546063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8546063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","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/A5101744663","display_name":"Chenxing Li","orcid":"https://orcid.org/0009-0001-4226-7825"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394072","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0003-1685-7968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["AI Lab, Rokid Inc., Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Rokid Inc., Beijing, P.R.China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004363895","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-3576-6914"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362398","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0002-1290-6972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["AI Lab, Rokid Inc., Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Rokid Inc., Beijing, P.R.China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065635207","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-6379-7617"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101744663"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68731131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4274","issue":null,"first_page":"3222","last_page":"3227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.7760947346687317},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5730594992637634},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5286346673965454},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.510684072971344},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4916256070137024},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4641123414039612},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4139788746833801},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41394996643066406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3995450735092163},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12057960033416748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760947346687317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5730594992637634},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5286346673965454},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.510684072971344},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4916256070137024},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4641123414039612},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4139788746833801},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41394996643066406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3995450735092163},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12057960033416748},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/icpr.2018.8546063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8546063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1489125746","https://openalex.org/W1496120315","https://openalex.org/W1526236009","https://openalex.org/W1560013842","https://openalex.org/W2011865252","https://openalex.org/W2017921836","https://openalex.org/W2034940213","https://openalex.org/W2069737407","https://openalex.org/W2078953162","https://openalex.org/W2085628288","https://openalex.org/W2087402357","https://openalex.org/W2097207027","https://openalex.org/W2103635001","https://openalex.org/W2144499799","https://openalex.org/W2164890161","https://openalex.org/W2293634267","https://openalex.org/W2407023693","https://openalex.org/W2513938599","https://openalex.org/W2608183891","https://openalex.org/W2613303405","https://openalex.org/W2652238127","https://openalex.org/W2963920996","https://openalex.org/W6604666349","https://openalex.org/W6629052376","https://openalex.org/W6684337689","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W50892825","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,22],"propose":[4],"a":[5,24,68,125],"small-footprint":[6],"wake-up-word":[7,70],"speech":[8],"recognition":[9],"(WUWSR)":[10],"system":[11,80,92,118,127,146],"based":[12,128],"on":[13,129],"long":[14],"short-term":[15],"memory":[16],"(LSTM)":[17],"recurrent":[18],"neural":[19,132],"network,":[20],"and":[21,86],"design":[23],"novel":[25],"back-end":[26,141],"calibration":[27],"scoring":[28],"method":[29],"named":[30],"modified":[31],"zero":[32],"normalization":[33],"(MZN).":[34],"First,":[35],"LSTM":[36,137],"is":[37,48,58,71,105],"trained":[38],"to":[39,50,54,61,74],"predict":[40],"posterior":[41,52],"probability":[42,53],"of":[43],"context-dependent":[44],"state.":[45],"Next,":[46],"MZN":[47,142],"adopted":[49,106],"transfer":[51],"normalized":[55],"score,":[56],"which":[57],"then":[59],"converted":[60],"confidence":[62,76],"score":[63],"by":[64,97],"dynamic":[65],"programming.":[66],"Finally,":[67],"certain":[69],"recognized":[72],"according":[73],"the":[75,108,115,135],"score.":[77],"This":[78,91],"WUWSR":[79,145],"can":[81,93,147],"recognize":[82],"multiple":[83],"wake-up":[84,88],"words":[85,89],"change":[87],"flexibly.":[90],"guarantee":[94],"low":[95],"latency":[96],"omitting":[98],"decoding":[99],"network.":[100,133],"Equal":[101],"error":[102],"rate":[103],"(EER)":[104],"as":[107],"evaluation":[109],"metric.":[110],"Experimental":[111],"results":[112],"show":[113],"that":[114],"proposed":[116],"LSTM-based":[117],"achieves":[119],"33.33%":[120],"relative":[121,150],"improvement":[122],"compared":[123],"with":[124,140],"baseline":[126],"deep":[130],"feed-forward":[131],"Combining":[134],"front-end":[136],"acoustic":[138],"model":[139],"method,":[143],"our":[144],"achieve":[148],"51.92%":[149],"improvement.":[151]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}