{"id":"https://openalex.org/W3202151878","doi":"https://doi.org/10.1109/asru51503.2021.9688299","title":"Tiny-CRNN: Streaming Wakeword Detection in a Low Footprint Setting","display_name":"Tiny-CRNN: Streaming Wakeword Detection in a Low Footprint Setting","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3202151878","doi":"https://doi.org/10.1109/asru51503.2021.9688299","mag":"3202151878"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688299","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.14725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070084977","display_name":"Mohammad Omar Khursheed","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Omar Khursheed","raw_affiliation_strings":["University of Massachusetts,Amherst,MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst,MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042851905","display_name":"Christin Jose","orcid":"https://orcid.org/0000-0002-7594-4490"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christin Jose","raw_affiliation_strings":["Amazon Alexa Research,USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Research,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082530526","display_name":"Rajath Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajath Kumar","raw_affiliation_strings":["Amazon Alexa Research,USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Research,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070417","display_name":"Geng-Shen Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gengshen Fu","raw_affiliation_strings":["Amazon Alexa Research,USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Research,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049134079","display_name":"Brian Kulis","orcid":"https://orcid.org/0000-0002-1704-3838"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kulis","raw_affiliation_strings":["Amazon Alexa Research,USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Research,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005677843","display_name":"Santosh Kumar Cheekatmalla","orcid":"https://orcid.org/0000-0003-1144-4507"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santosh Kumar Cheekatmalla","raw_affiliation_strings":["Amazon Alexa Research,USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Research,USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070084977"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06191117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"541","last_page":"547"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.7691836953163147},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6411412954330444},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6401557326316833},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5882605314254761},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5570787787437439},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5452703237533569},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5090667605400085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3964676856994629},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3854840099811554},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32108527421951294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11535078287124634},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06438404321670532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691836953163147},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6411412954330444},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6401557326316833},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5882605314254761},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5570787787437439},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5452703237533569},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5090667605400085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3964676856994629},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3854840099811554},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32108527421951294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11535078287124634},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06438404321670532},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688299","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.14725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.14725","pdf_url":"https://arxiv.org/pdf/2109.14725","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":"","raw_type":"text"},{"id":"mag:3202151878","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.14725","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2109.14725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.14725","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.14725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.14725","pdf_url":"https://arxiv.org/pdf/2109.14725","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202151878.pdf","grobid_xml":"https://content.openalex.org/works/W3202151878.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2056986588","https://openalex.org/W2122797512","https://openalex.org/W2147489851","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2602634800","https://openalex.org/W2953219395","https://openalex.org/W2962707338","https://openalex.org/W3025581723","https://openalex.org/W3037988796","https://openalex.org/W3093383631","https://openalex.org/W3095735913","https://openalex.org/W3096662840","https://openalex.org/W3138218066","https://openalex.org/W6640212811","https://openalex.org/W6784198588"],"related_works":["https://openalex.org/W2953219395","https://openalex.org/W3195381335","https://openalex.org/W3103843209","https://openalex.org/W2528303662","https://openalex.org/W2755334444","https://openalex.org/W2615134457","https://openalex.org/W3165698711","https://openalex.org/W3214436459","https://openalex.org/W3198685759","https://openalex.org/W2337746211","https://openalex.org/W2984315264","https://openalex.org/W2802592911","https://openalex.org/W3006769269","https://openalex.org/W2972717820","https://openalex.org/W3202728214","https://openalex.org/W2938366133","https://openalex.org/W2575345876","https://openalex.org/W3021469861","https://openalex.org/W2976833605","https://openalex.org/W2786460214"],"abstract_inverted_index":{"In":[0],"this":[1,106],"work,":[2],"we":[3,64],"propose":[4],"Tiny-CRNN":[5,61],"(Tiny":[6],"Convolutional":[7,32],"Recurrent":[8],"Neural":[9,33,89],"Network)":[10],"models":[11,57],"applied":[12],"to":[13,31,68,86,95,120],"the":[14,60,96],"problem":[15,98],"of":[16,99],"wakeword":[17],"detection,":[18],"and":[19,63,116,123],"augment":[20],"them":[21],"with":[22,48,79,105],"scaled":[23],"dot":[24],"product":[25],"attention.":[26],"We":[27,92],"find":[28],"that,":[29],"compared":[30,85],"Network":[34,90],"models,":[35],"False":[36,72],"Accepts":[37,73],"in":[38,52,71,82,112,118],"a":[39,49,75],"250k":[40],"parameter":[41,53,77,83],"budget":[42,78],"can":[43,65],"be":[44],"reduced":[45],"by":[46,55],"25%":[47],"10%":[50],"reduction":[51,70,81],"size":[54,84],"using":[56],"based":[58],"on":[59,102],"architecture,":[62,107],"get":[66],"up":[67],"32%":[69],"at":[74],"50k":[76],"75%":[80],"word-level":[87],"Dense":[88],"models.":[91,125],"discuss":[93],"solutions":[94],"challenging":[97],"performing":[100],"inference":[101],"streaming":[103],"audio":[104],"as":[108,110],"well":[109],"differences":[111],"start-end":[113],"index":[114],"errors":[115],"latency":[117],"comparison":[119],"CNN,":[121],"DNN,":[122],"DNN-HMM":[124]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}