{"id":"https://openalex.org/W4386764531","doi":"https://doi.org/10.1109/waspaa58266.2023.10248052","title":"Towards on-Device Keyword Spotting using Low-Footprint Quaternion Neural Models","display_name":"Towards on-Device Keyword Spotting using Low-Footprint Quaternion Neural Models","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764531","doi":"https://doi.org/10.1109/waspaa58266.2023.10248052"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5021015421","display_name":"Aryan Chaudhary","orcid":"https://orcid.org/0000-0002-4751-9542"},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]},{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aryan Chaudhary","raw_affiliation_strings":["IIIT Delhi,CSE Department and Infosys Centre for AI,India","CSE Department and Infosys Centre for AI, IIIT Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi,CSE Department and Infosys Centre for AI,India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]},{"raw_affiliation_string":"CSE Department and Infosys Centre for AI, IIIT Delhi, India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075520691","display_name":"Vinayak Abrol","orcid":"https://orcid.org/0000-0001-8149-8151"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]},{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinayak Abrol","raw_affiliation_strings":["IIIT Delhi,CSE Department and Infosys Centre for AI,India","CSE Department and Infosys Centre for AI, IIIT Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi,CSE Department and Infosys Centre for AI,India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]},{"raw_affiliation_string":"CSE Department and Infosys Centre for AI, IIIT Delhi, India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021015421"],"corresponding_institution_ids":["https://openalex.org/I110675161","https://openalex.org/I119939252","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.1983,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44433424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/quaternion","display_name":"Quaternion","score":0.8764641284942627},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7826363444328308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.769328773021698},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5325416922569275},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5194739699363708},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5107665061950684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5022933483123779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38557934761047363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11002632975578308}],"concepts":[{"id":"https://openalex.org/C200127275","wikidata":"https://www.wikidata.org/wiki/Q173853","display_name":"Quaternion","level":2,"score":0.8764641284942627},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7826363444328308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769328773021698},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5325416922569275},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5194739699363708},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5107665061950684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022933483123779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38557934761047363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11002632975578308},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"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":25,"referenced_works":["https://openalex.org/W2028547769","https://openalex.org/W2143612262","https://openalex.org/W2194775991","https://openalex.org/W2407023693","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2905556235","https://openalex.org/W2963230471","https://openalex.org/W2963585199","https://openalex.org/W2963719423","https://openalex.org/W2972717745","https://openalex.org/W3006197067","https://openalex.org/W3025581723","https://openalex.org/W3034892239","https://openalex.org/W3037695800","https://openalex.org/W3097018422","https://openalex.org/W3097681340","https://openalex.org/W3138218066","https://openalex.org/W3178985214","https://openalex.org/W3196496149","https://openalex.org/W3196682461","https://openalex.org/W3198035615","https://openalex.org/W4225328536","https://openalex.org/W4310253046","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W3018114492","https://openalex.org/W3160200750","https://openalex.org/W4248007934","https://openalex.org/W2323788589","https://openalex.org/W1554833030","https://openalex.org/W3091664389","https://openalex.org/W4308521107","https://openalex.org/W2742860341","https://openalex.org/W4386764531","https://openalex.org/W2407023693"],"abstract_inverted_index":{"On-device":[0],"keyword":[1],"spotting":[2],"(KWS)":[3],"is":[4,31],"an":[5,52,123],"essential":[6],"component":[7],"for":[8,54,58],"wake-up":[9],"and":[10,25],"user":[11],"interaction":[12],"on":[13,23,103],"smart":[14],"edge":[15],"devices.":[16],"Existing":[17],"low-footprint":[18],"models":[19,50,63,85,102,111],"are":[20],"mainly":[21],"based":[22],"2D":[24],"1D":[26],"convolutions,":[27],"where":[28,109],"the":[29,37,59,72,76,99,104,127,131],"former":[30],"better":[32],"at":[33],"capturing":[34],"invariances":[35],"while":[36],"latter":[38],"enables":[39],"faster":[40],"inference":[41],"times.":[42],"In":[43,118],"this":[44,94],"work,":[45],"we":[46,120],"explore":[47],"Quaternion":[48,62],"neural":[49],"as":[51,86],"alternative":[53],"effective":[55],"acoustic":[56],"modeling":[57],"KWS":[60,101],"task.":[61],"can":[64],"embed":[65],"various":[66],"facets":[67],"of":[68,75,98,126],"input":[69],"features":[70],"within":[71],"multiple":[73],"dimensions":[74],"quaternion":[77,96,132],"space.":[78],"This":[79],"leads":[80],"to":[81,88,115,134],"smaller":[82],"&":[83],"efficient":[84],"compared":[87],"their":[89,136],"conventional":[90],"counterparts.":[91],"We":[92],"demonstrate":[93],"using":[95],"versions":[97],"popular":[100],"Google":[105],"Command":[106],"V2":[107],"dataset,":[108],"our":[110],"achieve":[112],"comparable":[113],"performance":[114],"existing":[116],"ones.":[117],"addition,":[119],"also":[121],"provide":[122],"extensive":[124],"analysis":[125],"learning":[128],"behavior":[129],"in":[130,138],"network":[133],"motivate":[135],"use":[137],"other":[139],"speech/audio":[140],"tasks.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}