{"id":"https://openalex.org/W3152754274","doi":"https://doi.org/10.1145/3404835.3462964","title":"Multimodal Activation: Awakening Dialog Robots without Wake Words","display_name":"Multimodal Activation: Awakening Dialog Robots without Wake Words","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3152754274","doi":"https://doi.org/10.1145/3404835.3462964","mag":"3152754274"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Shandong University, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Shandong, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011592556","display_name":"Mengzhao Jia","orcid":"https://orcid.org/0009-0005-9759-4996"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhao Jia","raw_affiliation_strings":["Shandong University, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Shandong, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072768866","display_name":"Xuemeng Song","orcid":"https://orcid.org/0000-0002-5274-4197"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemeng Song","raw_affiliation_strings":["Shandong University, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Shandong, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112630557","display_name":"Ganglu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ganglu Wu","raw_affiliation_strings":["Alibaba Group, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059602960","display_name":"Harry H. Cheng","orcid":"https://orcid.org/0000-0001-7436-0162"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Harry Cheng","raw_affiliation_strings":["Shandong University, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Shandong, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101513424","display_name":"Jian Gu","orcid":"https://orcid.org/0009-0004-2418-0170"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Gu","raw_affiliation_strings":["Alibaba Group, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038612499"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.8729,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75140012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7824767827987671},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6420104503631592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5293474793434143},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5105768442153931},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4540945887565613},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.4524967074394226},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44987359642982483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4427635669708252},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4231986999511719},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4226803481578827},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37518835067749023},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1172376275062561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824767827987671},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6420104503631592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5293474793434143},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5105768442153931},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4540945887565613},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.4524967074394226},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44987359642982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4427635669708252},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4231986999511719},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4226803481578827},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37518835067749023},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1172376275062561},{"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:10.1145/3404835.3462964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1983364832","https://openalex.org/W1985909009","https://openalex.org/W2011865252","https://openalex.org/W2033068372","https://openalex.org/W2042608483","https://openalex.org/W2061489198","https://openalex.org/W2082942761","https://openalex.org/W2122591539","https://openalex.org/W2153962611","https://openalex.org/W2162813706","https://openalex.org/W2474516730","https://openalex.org/W2738406145","https://openalex.org/W2787581402","https://openalex.org/W2792106437","https://openalex.org/W2924126491","https://openalex.org/W2953436475","https://openalex.org/W2953561866","https://openalex.org/W2963115079","https://openalex.org/W2963524571","https://openalex.org/W2964010806","https://openalex.org/W2964346351","https://openalex.org/W2973020025","https://openalex.org/W2985588979","https://openalex.org/W3035260104","https://openalex.org/W3093949709","https://openalex.org/W3196434891"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W4243161226","https://openalex.org/W2950647290","https://openalex.org/W2620829895","https://openalex.org/W2356918560","https://openalex.org/W1968481813","https://openalex.org/W2392886708"],"abstract_inverted_index":{"When":[0],"talking":[1,81,148,172],"to":[2,8,89,101,127,144,167,180],"the":[3,10,14,43,55,91,94,105,110,116,129,135,146,151,155,158,169,204],"dialog":[4,34],"robots,":[5],"users":[6],"have":[7,36],"activate":[9],"robot":[11,56],"first":[12,85],"from":[13,109],"standby":[15],"mode":[16],"with":[17,39],"special":[18],"wake":[19,58],"words,":[20],"such":[21],"as":[22],"\"Hey":[23],"Siri\",":[24],"which":[25],"is":[26,87,143,160,165],"apparently":[27],"not":[28],"user-friendly.":[29],"The":[30,84,140],"latest":[31],"generation":[32],"of":[33,72,115,150,157,206],"robots":[35],"been":[37],"equipped":[38],"advanced":[40],"sensors,":[41],"like":[42],"camera,":[44],"enabling":[45],"multimodal":[46],"activation.":[47],"In":[48],"this":[49,62,119],"work,":[50],"we":[51,64,188],"work":[52],"towards":[53],"awaking":[54],"without":[57],"words.":[59],"To":[60,185],"accomplish":[61],"task,":[63],"present":[65],"a":[66,190],"Multimodal":[67],"Activation":[68],"Scheme":[69],"(MAS),":[70],"consisting":[71],"two":[73,121,183],"key":[74],"components:":[75],"audio-visual":[76],"consistency":[77,92],"detection":[78],"and":[79,96,134,162],"semantic":[80,147],"intention":[82,149],"inference.":[83],"one":[86,142],"devised":[88],"measure":[90],"between":[93],"audio":[95,137],"visual":[97],"modalities":[98],"in":[99,113],"order":[100],"figure":[102],"out":[103],"weather":[104],"heard":[106],"speech":[107,159],"comes":[108],"detected":[111],"user":[112],"front":[114],"camera.":[117],"Towards":[118],"end,":[120],"heterogeneous":[122],"CNN-based":[123],"networks":[124],"are":[125],"introduced":[126],"convolutionalize":[128],"fine-grained":[130],"facial":[131],"landmark":[132],"features":[133],"MFCC":[136],"features,":[138],"respectively.":[139],"second":[141],"infer":[145],"recorded":[152,196],"speech,":[153],"where":[154],"transcript":[156],"recognized":[161],"matrix":[163],"factorization":[164],"utilized":[166],"uncover":[168],"latent":[170],"human-robot":[171],"topics.":[173],"We":[174],"ultimately":[175],"devise":[176],"different":[177],"fusion":[178],"strategies":[179],"unify":[181],"these":[182],"components.":[184],"evaluate":[186],"MAS,":[187],"construct":[189],"dataset":[191],"containing":[192],"12,741":[193],"short":[194],"videos":[195],"by":[197],"194":[198],"invited":[199],"volunteers.":[200],"Extensive":[201],"experiments":[202],"demonstrate":[203],"effectiveness":[205],"our":[207],"scheme.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}