{"id":"https://openalex.org/W4375869243","doi":"https://doi.org/10.1109/icassp49357.2023.10095534","title":"Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers","display_name":"Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869243","doi":"https://doi.org/10.1109/icassp49357.2023.10095534"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095534","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Xiaomi Corperation,Beijing,China","Xiaomi Corperation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corperation,Beijing,China","Xiaomi Corperation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364004","display_name":"Zhiyong Yan","orcid":"https://orcid.org/0000-0003-3596-9463"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corperation,Beijing,China","Xiaomi Corperation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corperation,Beijing,China","Xiaomi Corperation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corperation,Beijing,China","Xiaomi Corperation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080154283"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":0.6113,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63530516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.93068528175354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8568165302276611},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6419345736503601},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.632064163684845},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6226101517677307},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5817793011665344},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5512292981147766},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5402398705482483},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5376746654510498},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41509705781936646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4074450731277466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4012485146522522},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1332261860370636},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10036706924438477}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.93068528175354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568165302276611},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6419345736503601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.632064163684845},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6226101517677307},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5817793011665344},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5512292981147766},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5402398705482483},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5376746654510498},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41509705781936646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074450731277466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4012485146522522},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1332261860370636},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10036706924438477},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/icassp49357.2023.10095534","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2407023693","https://openalex.org/W2593116425","https://openalex.org/W2797583228","https://openalex.org/W2887528618","https://openalex.org/W2899663614","https://openalex.org/W2936774411","https://openalex.org/W2963163009","https://openalex.org/W2973226577","https://openalex.org/W3082696729","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3097018422","https://openalex.org/W3126565544","https://openalex.org/W3153215492","https://openalex.org/W3163237592","https://openalex.org/W3163571828","https://openalex.org/W3163621198","https://openalex.org/W3196296753","https://openalex.org/W3196496149","https://openalex.org/W3196974791","https://openalex.org/W3198035615","https://openalex.org/W3198850376","https://openalex.org/W4224916413","https://openalex.org/W4224917059","https://openalex.org/W4226046733","https://openalex.org/W4285483774","https://openalex.org/W4286904253","https://openalex.org/W4286909525","https://openalex.org/W4295312788","https://openalex.org/W4296068594","https://openalex.org/W4296068805","https://openalex.org/W4296932804","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6753500843","https://openalex.org/W6755977528","https://openalex.org/W6766978945","https://openalex.org/W6790117948","https://openalex.org/W6802298259","https://openalex.org/W6803049385","https://openalex.org/W6843425716"],"related_works":["https://openalex.org/W2742860341","https://openalex.org/W4248007934","https://openalex.org/W3018114492","https://openalex.org/W1483316057","https://openalex.org/W1554833030","https://openalex.org/W2323788589","https://openalex.org/W2058491579","https://openalex.org/W2769949010","https://openalex.org/W1989446525","https://openalex.org/W2123506935"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"(KWS)":[2],"is":[3],"a":[4,15,34,47,117,125],"core":[5],"human-machine-interaction":[6],"front-end":[7],"task":[8],"for":[9],"most":[10],"modern":[11],"intelligent":[12],"assistants.":[13],"Recently,":[14],"unified":[16],"(UniKW-AT)":[17],"framework":[18],"has":[19],"been":[20],"proposed":[21,103,112],"that":[22,110],"adds":[23],"additional":[24],"capabilities":[25],"in":[26],"the":[27,43,92,111],"form":[28],"of":[29,46,82,89,119],"audio":[30],"tagging":[31],"(AT)":[32],"to":[33],"KWS":[35],"model.":[36],"However,":[37],"previous":[38],"work":[39,66],"did":[40],"not":[41],"consider":[42],"real-world":[44],"deployment":[45],"UniKW-AT":[48],"model,":[49],"where":[50],"factors":[51],"such":[52],"as":[53],"model":[54,78],"size":[55],"and":[56,86],"inference":[57],"speed":[58],"are":[59],"more":[60],"important":[61],"than":[62],"performance":[63],"alone.":[64],"This":[65],"introduces":[67],"three":[68],"mobile-device":[69],"deployable":[70],"models":[71,114],"named":[72],"Unified":[73],"Transformers":[74],"(UiT).":[75],"Our":[76],"best":[77],"achieves":[79],"an":[80,87],"mAP":[81],"34.09":[83],"on":[84,91,105],"Audioset,":[85],"accuracy":[88],"97.76":[90],"public":[93],"Google":[94],"Speech":[95],"Commands":[96],"V1":[97],"dataset.":[98],"Further,":[99],"we":[100],"benchmark":[101],"our":[102],"approaches":[104],"four":[106],"mobile":[107],"platforms,":[108],"revealing":[109],"UiT":[113],"can":[115],"achieve":[116],"speedup":[118],"2":[120],"-":[121],"6":[122],"times":[123],"against":[124],"competitive":[126],"MobileNetV2.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
