{"id":"https://openalex.org/W3207904293","doi":null,"title":"Power efficient analog features for audio recognition.","display_name":"Power efficient analog features for audio recognition.","publication_year":2021,"publication_date":"2021-10-07","ids":{"openalex":"https://openalex.org/W3207904293","mag":"3207904293"},"language":"en","primary_location":{"id":"mag:3207904293","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.03715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.03715","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090460379","display_name":"Boris Bergsma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Bergsma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056559993","display_name":"Minhao Yang","orcid":"https://orcid.org/0000-0003-1141-4818","observed_orcids":["https://orcid.org/0000-0003-1141-4818"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minhao Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1141-4818","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491","observed_orcids":["https://orcid.org/0000-0002-5569-9491"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milo\u0161 Cer\u0148ak","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5569-9491","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6201000213623047,"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":0.6201000213623047,"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":0.328900009393692,"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":0.03660000115633011,"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/analog-electronics","display_name":"analog electronics","score":0.550000011920929},{"id":"https://openalex.org/keywords/power-efficiency","display_name":"power efficiency","score":0.6610000133514404},{"id":"https://openalex.org/keywords/sound-recognition","display_name":"sound recognition","score":0.7020000219345093},{"id":"https://openalex.org/keywords/wake-word-detection","display_name":"wake word detection","score":0.7480000257492065},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"keyword spotting","score":1.0},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.9990000128746033},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.7829999923706055},{"id":"https://openalex.org/keywords/bandpass-filtering","display_name":"bandpass filtering","score":0.8539999723434448},{"id":"https://openalex.org/keywords/information-theory","display_name":"information theory","score":0.8220000267028809},{"id":"https://openalex.org/keywords/information-flow","display_name":"information flow","score":0.8339999914169312},{"id":"https://openalex.org/keywords/performance-bottlenecks","display_name":"performance bottlenecks","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489866614341736},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6012860536575317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4588637053966522},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.44724103808403015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.427713006734848},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.41020357608795166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38171011209487915},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29060089588165283},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3207904293","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.03715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3207904293","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.03715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1995875735","https://openalex.org/W2088964664","https://openalex.org/W2112796928","https://openalex.org/W2797583228","https://openalex.org/W2936774411","https://openalex.org/W2944779197","https://openalex.org/W2946948417","https://openalex.org/W2974831423","https://openalex.org/W2982265383","https://openalex.org/W2995929068","https://openalex.org/W3015305007","https://openalex.org/W3104334086"],"related_works":["https://openalex.org/W4297841247","https://openalex.org/W4366457353","https://openalex.org/W4312309180","https://openalex.org/W2503574126","https://openalex.org/W4286571865","https://openalex.org/W4400811435","https://openalex.org/W2113162324","https://openalex.org/W3159337302","https://openalex.org/W3157976301","https://openalex.org/W4385656556"],"abstract_inverted_index":{"The":[0,83,149,172],"digital":[1,41,103,169],"signal":[2],"processing-based":[3],"representations":[4],"like":[5,49],"the":[6,40,59,90,146,168,178],"Mel-Frequency":[7],"Cepstral":[8],"Coefficient":[9],"are":[10,93,118,152],"well":[11],"known":[12],"to":[13,131,156,180],"be":[14,54],"a":[15,123,157],"solid":[16],"basis":[17],"for":[18],"various":[19],"audio":[20],"processing":[21,68],"tasks.":[22],"Alternatively,":[23],"analog":[24,63,91],"feature":[25,141],"representations,":[26],"relying":[27],"on":[28,46,65,99,111,128],"analog-electronics-feasible":[29],"bandpass":[30],"filtering,":[31],"allow":[32],"much":[33],"lower":[34],"system":[35],"power":[36,185],"consumption":[37,186],"compared":[38],"with":[39],"counterpart,":[42],"while":[43],"parity":[44],"performance":[45,109,134,147],"traditional":[47],"tasks":[48,69,101,114],"voice":[50],"activity":[51],"detection":[52],"can":[53],"achieved.":[55],"This":[56],"work":[57],"explores":[58],"possibility":[60],"of":[61,85,159,162],"using":[62],"features":[64,92,104],"multiple":[66],"speech":[67],"that":[70,89],"vary":[71],"in":[72,140],"time":[73],"dependencies:":[74],"wake":[75],"word":[76],"detection,":[77],"keyword":[78,163],"spotting,":[79],"and":[80,97,184],"speaker":[81],"identification.":[82],"results":[84],"this":[86,133],"evaluation":[87],"show":[88],"still":[94],"more":[95,112],"power-efficient":[96],"competitive":[98],"simpler":[100],"than":[102],"but":[105],"yield":[106],"an":[107],"increasing":[108],"drop":[110,135],"complex":[113],"when":[115],"long-time":[116],"correlations":[117],"present.":[119],"We":[120],"also":[121],"introduce":[122],"novel":[124],"theoretical":[125,150],"framework":[126],"based":[127],"information":[129,138],"theory":[130],"understand":[132],"by":[136],"quantifying":[137],"flow":[139],"calculation":[142],"which":[143],"helps":[144],"identify":[145],"bottlenecks.":[148],"claims":[151],"experimentally":[153],"validated,":[154],"leading":[155],"maximum":[158],"6%":[160],"increase":[161],"spotting":[164],"accuracy,":[165],"even":[166],"surpassing":[167],"baseline":[170],"features.":[171],"proposed":[173],"analog-feature-based":[174],"systems":[175],"could":[176],"pave":[177],"way":[179],"achieving":[181],"best-in-class":[182],"accuracy":[183],"simultaneously.":[187]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-10-25T00:00:00"}