{"id":"https://openalex.org/W4283694719","doi":"https://doi.org/10.21437/interspeech.2022-11080","title":"QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer","display_name":"QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283694719","doi":"https://doi.org/10.21437/interspeech.2022-11080"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11080","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11080","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":"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/A5062106974","display_name":"Jinmiao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2818286","display_name":"LG (United States)","ror":"https://ror.org/02b948n83","country_code":"US","type":"company","lineage":["https://openalex.org/I2818286","https://openalex.org/I4210131320"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinmiao Huang","raw_affiliation_strings":["LG Electronics Toronto AI Lab"],"affiliations":[{"raw_affiliation_string":"LG Electronics Toronto AI Lab","institution_ids":["https://openalex.org/I2818286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051092022","display_name":"Waseem Gharbieh","orcid":null},"institutions":[{"id":"https://openalex.org/I2818286","display_name":"LG (United States)","ror":"https://ror.org/02b948n83","country_code":"US","type":"company","lineage":["https://openalex.org/I2818286","https://openalex.org/I4210131320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Waseem Gharbieh","raw_affiliation_strings":["LG Electronics Toronto AI Lab"],"affiliations":[{"raw_affiliation_string":"LG Electronics Toronto AI Lab","institution_ids":["https://openalex.org/I2818286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000225161","display_name":"Qianhui Wan","orcid":"https://orcid.org/0000-0003-4207-4940"},"institutions":[{"id":"https://openalex.org/I2818286","display_name":"LG (United States)","ror":"https://ror.org/02b948n83","country_code":"US","type":"company","lineage":["https://openalex.org/I2818286","https://openalex.org/I4210131320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qianhui Wan","raw_affiliation_strings":["LG Electronics Toronto AI Lab"],"affiliations":[{"raw_affiliation_string":"LG Electronics Toronto AI Lab","institution_ids":["https://openalex.org/I2818286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025143578","display_name":"Han Suk Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I2818286","display_name":"LG (United States)","ror":"https://ror.org/02b948n83","country_code":"US","type":"company","lineage":["https://openalex.org/I2818286","https://openalex.org/I4210131320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Suk Shim","raw_affiliation_strings":["LG Electronics Artificial Intelligence Lab"],"affiliations":[{"raw_affiliation_string":"LG Electronics Artificial Intelligence Lab","institution_ids":["https://openalex.org/I2818286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079946759","display_name":"Hyun\u2010Chul Lee","orcid":"https://orcid.org/0000-0002-2466-4667"},"institutions":[{"id":"https://openalex.org/I2818286","display_name":"LG (United States)","ror":"https://ror.org/02b948n83","country_code":"US","type":"company","lineage":["https://openalex.org/I2818286","https://openalex.org/I4210131320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyun Chul Lee","raw_affiliation_strings":["LG Electronics Artificial Intelligence Lab"],"affiliations":[{"raw_affiliation_string":"LG Electronics Artificial Intelligence Lab","institution_ids":["https://openalex.org/I2818286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062106974"],"corresponding_institution_ids":["https://openalex.org/I2818286"],"apc_list":null,"apc_paid":null,"fwci":0.5194,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61797027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5200","last_page":"5204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.8893344402313232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7908674478530884},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6705425381660461},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5554338097572327},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.49306318163871765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4046528935432434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39883512258529663},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06916174292564392}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8893344402313232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908674478530884},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6705425381660461},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5554338097572327},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.49306318163871765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4046528935432434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39883512258529663},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06916174292564392},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11080","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11080","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1485222997","https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W1553469512","https://openalex.org/W2019318646","https://openalex.org/W2034940213","https://openalex.org/W2407023693","https://openalex.org/W2510945575","https://openalex.org/W2696967604","https://openalex.org/W2747874407","https://openalex.org/W2899663614","https://openalex.org/W2955425717","https://openalex.org/W2962707338","https://openalex.org/W2962736743","https://openalex.org/W2963163009","https://openalex.org/W2972677972","https://openalex.org/W2972792496","https://openalex.org/W2973133192","https://openalex.org/W3045062880","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3095321517","https://openalex.org/W3104334086","https://openalex.org/W3157506437","https://openalex.org/W3157914380","https://openalex.org/W3163237592","https://openalex.org/W3163465952","https://openalex.org/W3196567456","https://openalex.org/W3197228895","https://openalex.org/W4239072543","https://openalex.org/W4287864706","https://openalex.org/W4289243832"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Current":[0],"keyword":[1,65],"spotting":[2,66],"systems":[3],"are":[4],"typically":[5],"trained":[6],"with":[7,68,102],"a":[8,30,97,109],"large":[9],"amount":[10],"of":[11,56,112],"pre-defined":[12],"keywords.Recognizing":[13],"keywords":[14],"in":[15,50,82],"an":[16],"open-vocabulary":[17,64],"setting":[18],"is":[19,36],"essential":[20],"for":[21],"personalizing":[22],"smart":[23],"device":[24],"interaction.Towards":[25],"this":[26],"goal,":[27],"we":[28],"propose":[29],"pure":[31],"MLP-based":[32],"neural":[33],"network":[34],"that":[35,44,76],"based":[37],"on":[38,89],"MLPMixer":[39,59],"-an":[40],"MLP":[41],"model":[42,106],"architecture":[43,60],"effectively":[45],"replaces":[46],"the":[47,58,62,69,91,118],"attention":[48],"mechanism":[49],"Vision":[51],"Transformers.We":[52],"investigate":[53],"different":[54],"ways":[55],"adapting":[57],"to":[61,117],"QbyE":[63],"task.Comparisons":[67],"state-of-the-art":[70],"RNN":[71],"and":[72,86,96,114],"CNN":[73],"models":[74],"show":[75],"our":[77],"method":[78],"achieves":[79],"better":[80],"performance":[81],"challenging":[83],"situations":[84],"(10dB":[85],"6dB":[87],"environments)":[88],"both":[90],"publicly":[92],"available":[93],"Hey-Snips":[94],"dataset":[95,101],"larger":[98],"scale":[99],"internal":[100],"400":[103],"speakers.Our":[104],"proposed":[105],"also":[107],"has":[108],"smaller":[110],"number":[111],"parameters":[113],"MACs":[115],"compared":[116],"baseline":[119],"models.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}