{"id":"https://openalex.org/W4296068594","doi":"https://doi.org/10.21437/interspeech.2022-607","title":"UniKW-AT: Unified Keyword Spotting and Audio Tagging","display_name":"UniKW-AT: Unified Keyword Spotting and Audio Tagging","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068594","doi":"https://doi.org/10.21437/interspeech.2022-607"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-607","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-607","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.11377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Xiaomi Corperation, Beijing, China"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corperation, Beijing, China"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corperation, Beijing, China"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corperation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362598","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-0921-0122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corperation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corperation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3238","last_page":"3242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.994700014591217,"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":0.989799976348877,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9678378105163574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8595365285873413},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7503530383110046},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6106675267219543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.579042911529541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47594118118286133},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.46836602687835693},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.45171526074409485},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44693267345428467},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3960478901863098},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.31163567304611206}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9678378105163574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595365285873413},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7503530383110046},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6106675267219543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.579042911529541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47594118118286133},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.46836602687835693},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45171526074409485},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44693267345428467},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3960478901863098},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.31163567304611206},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-607","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-607","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.11377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11377","pdf_url":"https://arxiv.org/pdf/2209.11377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.11377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11377","pdf_url":"https://arxiv.org/pdf/2209.11377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2219249508","https://openalex.org/W2407023693","https://openalex.org/W2593116425","https://openalex.org/W2797583228","https://openalex.org/W2963163009","https://openalex.org/W2973226577","https://openalex.org/W3082696729","https://openalex.org/W3094550259","https://openalex.org/W3126565544","https://openalex.org/W3139878283","https://openalex.org/W3162999565","https://openalex.org/W3163571828","https://openalex.org/W3196974791","https://openalex.org/W3198035615","https://openalex.org/W3205475937","https://openalex.org/W4205689591","https://openalex.org/W4221095487","https://openalex.org/W4224917059","https://openalex.org/W4226046733","https://openalex.org/W4286904253","https://openalex.org/W4286968695","https://openalex.org/W4287123098","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Within":[0],"the":[1,6,70,93,100,109,116,131,140],"audio":[2,12,52],"research":[3,22],"community":[4],"and":[5,11,21,66,83,115,134,169],"industry,":[7],"keyword":[8],"spotting":[9],"(KWS)":[10],"tagging":[13],"(AT)":[14],"are":[15,35,106],"seen":[16],"as":[17],"two":[18],"distinct":[19],"tasks":[20,34],"fields.":[23],"However,":[24],"from":[25],"a":[26,39,103,155,175],"technical":[27],"point":[28],"of":[29,32,102,128,137],"view,":[30],"both":[31,64],"these":[33],"identical:":[36],"they":[37],"predict":[38,79],"label":[40],"(keyword":[41],"in":[42,46],"KWS,":[43,73],"sound":[44,81,88],"event":[45],"AT)":[47],"for":[48,61,72],"some":[49],"fixed-sized":[50],"input":[51],"segment.":[53],"This":[54],"work":[55],"proposes":[56],"UniKW-AT:":[57],"An":[58],"initial":[59],"approach":[60,91],"jointly":[62],"training":[63],"KWS":[65,157,162,168],"AT.":[67],"UniKW-AT":[68],"enhances":[69],"noise-robustness":[71,149],"while":[74],"also":[75],"being":[76],"able":[77],"to":[78],"specific":[80],"events":[82],"enabling":[84],"conditional":[85],"wake-ups":[86],"on":[87,108,130,139,154],"events.":[89],"Our":[90,164],"extends":[92],"AT":[94,170],"pipeline":[95],"with":[96],"additional":[97],"labels":[98],"describing":[99],"presence":[101],"keyword.":[104],"Experiments":[105],"conducted":[107],"Google":[110],"Speech":[111],"Commands":[112],"V1":[113],"(GSCV1)":[114],"balanced":[117],"Audioset":[118],"(AS)":[119],"datasets.":[120],"The":[121],"proposed":[122],"MobileNetV2":[123],"model":[124],"achieves":[125],"an":[126,135],"accuracy":[127],"97.53%":[129],"GSCV1":[132],"dataset":[133],"mAP":[136],"33.4":[138],"AS":[141],"evaluation":[142],"set.":[143],"Further,":[144],"we":[145],"show":[146],"that":[147,167],"significant":[148,179],"gains":[150],"can":[151,171],"be":[152,172],"observed":[153],"real-world":[156],"dataset,":[158],"greatly":[159],"outperforming":[160],"standard":[161],"approaches.":[163],"study":[165],"shows":[166],"merged":[173],"into":[174],"single":[176],"framework":[177],"without":[178],"performance":[180],"degradation.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}