{"id":"https://openalex.org/W3193470517","doi":"https://doi.org/10.1145/3473714.3473731","title":"Application Research of Speech Instruction Recognition in Human-computer Interaction","display_name":"Application Research of Speech Instruction Recognition in Human-computer Interaction","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3193470517","doi":"https://doi.org/10.1145/3473714.3473731","mag":"3193470517"},"language":"en","primary_location":{"id":"doi:10.1145/3473714.3473731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3473714.3473731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 1st International Conference on Control and Intelligent Robotics","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/A5056242193","display_name":"Xiang Fu","orcid":"https://orcid.org/0000-0001-6577-2499"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiang Fu","raw_affiliation_strings":["Blue Sky Frontier Science and Technology Innovation Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Blue Sky Frontier Science and Technology Innovation Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655287","display_name":"Hongpeng Liu","orcid":"https://orcid.org/0000-0002-7494-9097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongpeng Liu","raw_affiliation_strings":["Blue Sky Frontier Science and Technology Innovation Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Blue Sky Frontier Science and Technology Innovation Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069642682","display_name":"Baojun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baojun Wang","raw_affiliation_strings":["School of Electronics and Information, Northwest Technology University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwest Technology University, Xi'an, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026096983","display_name":"Guiyong Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guiyong Yuan","raw_affiliation_strings":["Blue Sky Frontier Science and Technology Innovation Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Blue Sky Frontier Science and Technology Innovation Center, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396911","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-4527-9610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Blue Sky Frontier Science and Technology Innovation Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Blue Sky Frontier Science and Technology Innovation Center, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056242193"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5431962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"101"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9832000136375427,"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":0.8510438203811646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6803179979324341},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6204915642738342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5161396265029907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4966767430305481},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4963570237159729},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46138814091682434},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.44741079211235046},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4212602376937866},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4167570173740387},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.41068288683891296},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38538235425949097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510438203811646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6803179979324341},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6204915642738342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5161396265029907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966767430305481},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4963570237159729},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46138814091682434},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.44741079211235046},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4212602376937866},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4167570173740387},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.41068288683891296},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38538235425949097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3473714.3473731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3473714.3473731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 1st International Conference on Control and Intelligent Robotics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1689711448","https://openalex.org/W2102113734","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2520160253","https://openalex.org/W2526425061","https://openalex.org/W2566523535","https://openalex.org/W2576489192","https://openalex.org/W2808694371","https://openalex.org/W2926063217","https://openalex.org/W2945260553","https://openalex.org/W2963242190","https://openalex.org/W4248422158","https://openalex.org/W4299681030","https://openalex.org/W6637409405"],"related_works":["https://openalex.org/W3081952170","https://openalex.org/W4385719553","https://openalex.org/W2349696592","https://openalex.org/W642007152","https://openalex.org/W2083755708","https://openalex.org/W134179020","https://openalex.org/W4241475234","https://openalex.org/W596245619","https://openalex.org/W2525874696","https://openalex.org/W1540832706"],"abstract_inverted_index":{"Speech":[0],"instruction":[1,112,126,130,162,187,191],"recognition":[2,33,45,86,127,192],"is":[3,88,118,132,140],"an":[4,42,83,107],"important":[5],"research":[6,123],"direction":[7],"in":[8,102,195],"the":[9,18,30,58,79,94,103,109,121,156,169,218],"field":[10],"of":[11,20,98,114,124,137],"human":[12,222],"and":[13,24,71,120,128,153,179,203,223],"intelligent":[14,99,213],"machine":[15],"interaction.":[16],"With":[17],"development":[19],"deep":[21,49],"learning,":[22],"more":[23,25],"researchers":[26],"pay":[27],"attention":[28],"to":[29,65,76],"automatic":[31],"speech":[32,44,85,95,110,125,160,185,190,201],"technology":[34],"based":[35,47],"on":[36,48,175,182],"convolutional":[37,73],"neural":[38,50,74],"network.":[39],"By":[40],"establishing":[41],"end-to-end":[43,84],"model":[46,146,157],"network,":[51],"taking":[52,93],"logarithmic":[53],"amplitude":[54],"spectrum":[55],"features":[56],"as":[57,106],"network":[59,75],"input,":[60],"using":[61,72],"connectionist":[62],"temporal":[63],"classifiers":[64],"carry":[66],"out":[67],"time":[68],"sequence":[69],"classification,":[70],"deal":[77],"with":[78,147,158],"correlation":[80],"between":[81,221],"frames,":[82],"system":[87,193],"implemented.":[89],"On":[90],"this":[91,196],"basis,":[92],"interaction":[96],"scene":[97],"home":[100,116,214],"appliances":[101,117],"living":[104],"room":[105],"example,":[108],"control":[111,161,186],"database":[113],"smart":[115],"constructed,":[119],"application":[122],"data":[129,150,208],"generation":[131],"carried":[133],"out.":[134],"The":[135,164,189],"method":[136],"transfer":[138],"learning":[139],"adopted.":[141],"We":[142],"train":[143],"a":[144],"pre-training":[145],"open":[148],"source":[149],"set":[151],"firstly,":[152],"then":[154],"re-train":[155],"self-recorded":[159,184],"database.":[163,188],"experimental":[165],"results":[166],"show":[167],"that":[168,210],"proposed":[170],"algorithm":[171],"achieves":[172],"12.31%":[173],"WER":[174,181],"public":[176],"AISHELL-1":[177],"dataset":[178],"2.1%":[180],"our":[183],"realized":[194],"paper":[197],"can":[198,211],"quickly":[199],"recognize":[200],"instructions":[202,209],"convert":[204],"them":[205],"into":[206],"formatted":[207],"drive":[212],"appliances,":[215],"thus":[216],"improving":[217],"communication":[219],"efficiency":[220],"machine.":[224]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
