{"id":"https://openalex.org/W4375869483","doi":"https://doi.org/10.1109/icassp49357.2023.10097018","title":"HEiMDaL: Highly Efficient Method for Detection and Localization of Wake-Words","display_name":"HEiMDaL: Highly Efficient Method for Detection and Localization of Wake-Words","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869483","doi":"https://doi.org/10.1109/icassp49357.2023.10097018"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097018","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":"conference-paper","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/A5034953394","display_name":"Arnav Kundu","orcid":"https://orcid.org/0000-0003-2921-4312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnav Kundu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033081533","display_name":"Mohammad Samragh","orcid":"https://orcid.org/0000-0003-1404-527X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Samragh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076654","display_name":"Minsik Cho","orcid":"https://orcid.org/0000-0003-0481-2682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minsik Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028123060","display_name":"Priyanka Padmanabhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyanka Padmanabhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102495865","display_name":"Devang Naik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devang Naik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T12031","display_name":"Speech and dialogue systems","score":0.9952999949455261,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8247364163398743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134042024612427},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6550341844558716},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5889027118682861},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5870232582092285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5712689161300659},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5639181137084961},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5551747679710388},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.535223662853241},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.489907443523407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4660654366016388},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.4514642059803009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4016009569168091},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07115203142166138},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06245514750480652}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8247364163398743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134042024612427},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6550341844558716},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5889027118682861},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5870232582092285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5712689161300659},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5639181137084961},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5551747679710388},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.535223662853241},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.489907443523407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4660654366016388},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.4514642059803009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4016009569168091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07115203142166138},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06245514750480652},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097018","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":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1522301498","https://openalex.org/W1553469512","https://openalex.org/W2034940213","https://openalex.org/W2212465773","https://openalex.org/W2295088914","https://openalex.org/W2407023693","https://openalex.org/W2769912137","https://openalex.org/W2775572503","https://openalex.org/W2889511491","https://openalex.org/W2963351448","https://openalex.org/W2963977978","https://openalex.org/W2964187693","https://openalex.org/W3096831963","https://openalex.org/W3163074978","https://openalex.org/W3196496149","https://openalex.org/W4294621971","https://openalex.org/W6631190155","https://openalex.org/W6688089860","https://openalex.org/W6729959887","https://openalex.org/W6746451879","https://openalex.org/W6747003534","https://openalex.org/W6780998715"],"related_works":["https://openalex.org/W2388033618","https://openalex.org/W2886949521","https://openalex.org/W4400187963","https://openalex.org/W4205299633","https://openalex.org/W2034940213","https://openalex.org/W3120526039","https://openalex.org/W4287394695","https://openalex.org/W2019287799","https://openalex.org/W4367000378","https://openalex.org/W4402352431"],"abstract_inverted_index":{"Streaming":[0],"keyword":[1,119],"spotting":[2],"is":[3],"a":[4,156],"widely":[5,29],"used":[6],"solution":[7],"for":[8,155],"activating":[9],"voice":[10],"assistants.":[11],"Methods":[12],"based":[13],"on":[14],"Deep":[15],"Neural":[16],"Networks":[17],"with":[18,121,140,145],"Hidden":[19],"Markov":[20],"Model":[21],"(DNN-HMM)":[22],"have":[23],"proven":[24],"to":[25,39,82,99,113,125],"be":[26],"efficient":[27],"and":[28,41,45,67,101,144],"adopted":[30],"in":[31,104,136],"this":[32],"space,":[33],"primarily":[34],"because":[35],"of":[36,47,87,117,129],"the":[37,43,48,65,78,83,88,115,118,127,130,146],"ability":[38],"detect":[40,100,114],"identify":[42],"start":[44,128],"end":[46],"wake-up":[49],"word":[50],"at":[51],"low":[52,93],"compute":[53],"cost.":[54],"However,":[55],"such":[56],"hybrid":[57],"systems":[58],"suffer":[59],"from":[60],"loss":[61,112,124],"metric":[62],"mismatch":[63,80],"when":[64],"DNN":[66],"HMM":[68],"are":[69],"trained":[70],"independently.":[71],"Sequence":[72],"discriminative":[73],"training":[74],"cannot":[75],"fully":[76],"mitigate":[77],"loss-metric":[79],"due":[81],"inherent":[84],"Markovian":[85],"style":[86,153],"operation.":[89],"We":[90,107],"propose":[91],"an":[92,109,122],"footprint":[94,149],"CNN":[95],"model,":[96],"called":[97],"HEiMDaL,":[98],"localize":[102],"keywords":[103],"streaming":[105],"conditions.":[106],"introduce":[108],"alignment-based":[110],"classification":[111],"occurrence":[116],"along":[120,139],"offset":[123],"predict":[126],"keyword.":[131],"HEiMDaL":[132],"shows":[133],"73%":[134],"improvement":[135],"detection":[137],"metrics":[138],"equivalent":[141],"localization":[142],"accuracy":[143],"same":[147],"memory":[148],"as":[150],"existing":[151],"DNN-HMM":[152],"models":[154],"given":[157],"wake-word.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}