{"id":"https://openalex.org/W3015210390","doi":"https://doi.org/10.1109/icassp40776.2020.9054618","title":"Crnn-Ctc Based Mandarin Keywords Spotting","display_name":"Crnn-Ctc Based Mandarin Keywords Spotting","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015210390","doi":"https://doi.org/10.1109/icassp40776.2020.9054618","mag":"3015210390"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5078700905","display_name":"Haikang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haikang Yan","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101525745","display_name":"Wei Xie","orcid":"https://orcid.org/0000-0003-1770-8710"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xie","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078700905"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.7233,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87438403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7489","last_page":"7493"},"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":0.9973999857902527,"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":0.9932000041007996,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8859148621559143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8595215082168579},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7984911203384399},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7544990181922913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5953312516212463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5569860935211182},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5251067280769348},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4863446354866028},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35723045468330383},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35159215331077576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3229643702507019}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8859148621559143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595215082168579},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7984911203384399},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7544990181922913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953312516212463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5569860935211182},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5251067280769348},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4863446354866028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35723045468330383},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35159215331077576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3229643702507019},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W108550785","https://openalex.org/W179875071","https://openalex.org/W1553469512","https://openalex.org/W2028547769","https://openalex.org/W2034940213","https://openalex.org/W2097599384","https://openalex.org/W2122797512","https://openalex.org/W2127141656","https://openalex.org/W2127561697","https://openalex.org/W2137044559","https://openalex.org/W2193413348","https://openalex.org/W2254028986","https://openalex.org/W2407023693","https://openalex.org/W2543184722","https://openalex.org/W2558258029","https://openalex.org/W2602634800","https://openalex.org/W2612800309","https://openalex.org/W2888226713","https://openalex.org/W2889048668","https://openalex.org/W2939412000","https://openalex.org/W2944180060","https://openalex.org/W2953219395","https://openalex.org/W4294621971","https://openalex.org/W6604322312","https://openalex.org/W6607333740","https://openalex.org/W6687566353","https://openalex.org/W6714171909","https://openalex.org/W6729959887","https://openalex.org/W6753776127","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W4385352507","https://openalex.org/W2361574037","https://openalex.org/W2170821097","https://openalex.org/W3161425572"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"approaches":[3],"have":[4,20],"greatly":[5],"improved":[6],"the":[7,28,46,68,72],"performance":[8],"of":[9,16,74,86],"spoken":[10],"keyword":[11],"spotting":[12],"(KWS).":[13],"However,":[14],"KWS":[15,38],"different":[17],"languages":[18],"should":[19],"their":[21],"own":[22],"corresponding":[23],"modeling":[24,60],"units":[25],"to":[26],"optimize":[27],"performance.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"an":[35],"end-to-end":[36],"Mandarin":[37],"system":[39],"using":[40],"Convolutional":[41],"Recurrent":[42],"Neural":[43],"Network":[44],"with":[45,88,93],"Connectionist":[47],"Temporal":[48],"Classification":[49],"(CTC)":[50],"loss":[51],"function":[52],"(CRNN-CTC).":[53],"The":[54],"tonal":[55],"syllables":[56],"are":[57],"adopted":[58],"as":[59],"units.":[61],"Experiments":[62],"on":[63,71],"AISHELL-2":[64],"datasets":[65],"showed":[66],"that":[67],"proposed":[69],"approach":[70],"tasks":[73],"13":[75],"keywords":[76,79],"and":[77,91],"20":[78],"can":[80],"achieve":[81],"a":[82],"false":[83],"rejection":[84],"rate":[85],"5.35%":[87],"0.26":[89],"FA/hour":[90],"6.37%":[92],"0.17":[94],"FA/hour,":[95],"respectively.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}