{"id":"https://openalex.org/W2608183891","doi":"https://doi.org/10.1109/icpr.2016.7900073","title":"Wake-up-word spotting using end-to-end deep neural network system","display_name":"Wake-up-word spotting using end-to-end deep neural network system","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2608183891","doi":"https://doi.org/10.1109/icpr.2016.7900073","mag":"2608183891"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7900073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101618830","display_name":"Shilei Zhang","orcid":"https://orcid.org/0009-0007-5182-3065"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104039578","display_name":"Wen Liu","orcid":"https://orcid.org/0009-0006-2462-1356"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Liu","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2878","last_page":"2883"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/spotting","display_name":"Spotting","score":0.9118616580963135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8337950706481934},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7839093208312988},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7509332299232483},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7457704544067383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6344249844551086},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5965995788574219},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5554441809654236},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5529310703277588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115595459938049},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5034045577049255},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44005072116851807},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4180724322795868},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07109346985816956}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9118616580963135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337950706481934},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7839093208312988},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7509332299232483},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7457704544067383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6344249844551086},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5965995788574219},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5554441809654236},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5529310703277588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115595459938049},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5034045577049255},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44005072116851807},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4180724322795868},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07109346985816956},{"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2016.7900073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","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":27,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1553469512","https://openalex.org/W1981495752","https://openalex.org/W2011865252","https://openalex.org/W2028547769","https://openalex.org/W2034669856","https://openalex.org/W2034940213","https://openalex.org/W2102113734","https://openalex.org/W2111338354","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2397584766","https://openalex.org/W2407080277","https://openalex.org/W2407648438","https://openalex.org/W2560606416","https://openalex.org/W2963211739","https://openalex.org/W2963920996","https://openalex.org/W4285719527","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6712708045","https://openalex.org/W6713762819","https://openalex.org/W6713982112","https://openalex.org/W6730276982"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2545741539","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Deep":[0],"neural":[1,32],"networks":[2,33],"(DNNs)":[3],"have":[4],"tremendously":[5],"improved":[6],"the":[7,15,90,101,104,115,127],"performance":[8,25,102],"of":[9,103],"automatic":[10],"speech":[11,19],"recognition":[12,20],"(ASR).":[13],"On":[14],"other":[16],"hand,":[17],"end-to-end":[18,59],"system":[21,56,91],"can":[22,118],"achieve":[23],"state-of-the-art":[24],"using":[26],"Long":[27],"Short-Term":[28],"Memory":[29],"(LSTM)":[30],"recurrent":[31],"(RNNs)":[34],"and":[35,74,87,96],"Connectionist":[36],"Temporal":[37],"Classification":[38],"(CTC)":[39],"method":[40],"for":[41],"unsegmented":[42],"sequence":[43],"data.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"therefor":[49],"propose":[50],"a":[51,67,108,123],"lightweight":[52],"wake-up-word":[53],"(WUW)":[54],"spotting":[55,85,128],"based":[57],"on":[58,84,107],"DNN":[60],"architecture,":[61],"which":[62,112],"is":[63,79],"intended":[64],"to":[65,80,88],"provide":[66],"great":[68],"balance":[69],"between":[70],"decoding":[71],"speed,":[72],"accuracy":[73],"model":[75,94],"size.":[76],"The":[77],"objective":[78],"introduce":[81],"CTC":[82],"framework":[83],"process,":[86],"enhance":[89],"by":[92],"WUW-oriented":[93],"training":[95],"refinement":[97],"steps.":[98],"We":[99],"test":[100],"proposed":[105],"architecture":[106],"conversational":[109],"telephone":[110],"dataset":[111],"illustrate":[113],"that":[114],"computation":[116],"time":[117],"be":[119],"significantly":[120],"reduced":[121],"without":[122],"significant":[124],"decrease":[125],"in":[126],"accuracy.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}