{"id":"https://openalex.org/W4372268777","doi":"https://doi.org/10.1109/icassp49357.2023.10095360","title":"ERSAM: Neural Architecture Search for Energy-Efficient and Real-Time Social Ambiance Measurement","display_name":"ERSAM: Neural Architecture Search for Energy-Efficient and Real-Time Social Ambiance Measurement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372268777","doi":"https://doi.org/10.1109/icassp49357.2023.10095360"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095360","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095360","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":"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/A5065172226","display_name":"Chaojian Li","orcid":"https://orcid.org/0000-0003-4030-9777"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaojian Li","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA","Georgia Institute of Technology, Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077340762","display_name":"Wenwan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenwan Chen","raw_affiliation_strings":["Rice University,Houston,TX","Rice University, Houston, TX"],"affiliations":[{"raw_affiliation_string":"Rice University,Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, TX","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102865067","display_name":"Jiayi Yuan","orcid":"https://orcid.org/0009-0005-9208-6677"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Yuan","raw_affiliation_strings":["Rice University,Houston,TX","Rice University, Houston, TX"],"affiliations":[{"raw_affiliation_string":"Rice University,Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, TX","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019582323","display_name":"Yingyan Lin","orcid":"https://orcid.org/0000-0001-5946-203X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyan Celine Lin","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA","Georgia Institute of Technology, Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072109473","display_name":"Ashutosh Sabharwal","orcid":"https://orcid.org/0000-0003-1898-5787"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Sabharwal","raw_affiliation_strings":["Rice University,Houston,TX","Rice University, Houston, TX"],"affiliations":[{"raw_affiliation_string":"Rice University,Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, TX","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065172226"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03861801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","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":0.9940999746322632,"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":0.9940999746322632,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11519","display_name":"Digital Mental Health Interventions","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8394122123718262},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5739309787750244},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5599925518035889},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48948419094085693},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48808300495147705},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.47630608081817627},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4605104327201843},{"id":"https://openalex.org/keywords/mobile-phone","display_name":"Mobile phone","score":0.4396928548812866},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.41762423515319824},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34002596139907837},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20583680272102356},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13686010241508484},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12886270880699158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394122123718262},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5739309787750244},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5599925518035889},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48948419094085693},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48808300495147705},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.47630608081817627},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4605104327201843},{"id":"https://openalex.org/C2777421447","wikidata":"https://www.wikidata.org/wiki/Q17517","display_name":"Mobile phone","level":2,"score":0.4396928548812866},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.41762423515319824},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34002596139907837},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20583680272102356},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13686010241508484},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12886270880699158},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095360","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095360","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167608","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167608","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1577312970","https://openalex.org/W1821462560","https://openalex.org/W1963499862","https://openalex.org/W1977979148","https://openalex.org/W2108598243","https://openalex.org/W2219249508","https://openalex.org/W2791869963","https://openalex.org/W2898395910","https://openalex.org/W2900315145","https://openalex.org/W2936252403","https://openalex.org/W2951104886","https://openalex.org/W2963918968","https://openalex.org/W2964259004","https://openalex.org/W2967733054","https://openalex.org/W2973049979","https://openalex.org/W2982083293","https://openalex.org/W2994749257","https://openalex.org/W3015642076","https://openalex.org/W3015838662","https://openalex.org/W3034368386","https://openalex.org/W3034619943","https://openalex.org/W3036601975","https://openalex.org/W3045733287","https://openalex.org/W3081416955","https://openalex.org/W3082696729","https://openalex.org/W3095175338","https://openalex.org/W3095959945","https://openalex.org/W3096329809","https://openalex.org/W3096978537","https://openalex.org/W3109946440","https://openalex.org/W3137264163","https://openalex.org/W3138154797","https://openalex.org/W3190201952","https://openalex.org/W3195577433","https://openalex.org/W4221159017","https://openalex.org/W4281644254","https://openalex.org/W4312480718","https://openalex.org/W6638523607","https://openalex.org/W6688816777","https://openalex.org/W6752515464","https://openalex.org/W6756148602","https://openalex.org/W6756887525","https://openalex.org/W6767064347","https://openalex.org/W6780218876","https://openalex.org/W6785439968","https://openalex.org/W6790028984","https://openalex.org/W6800751262","https://openalex.org/W6804540981","https://openalex.org/W6809824710","https://openalex.org/W6839418328"],"related_works":["https://openalex.org/W3034529322","https://openalex.org/W2113597336","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"Social":[0],"ambiance":[1,197],"describes":[2],"the":[3,19,55,58,75,105,111,147,211],"context":[4],"in":[5,220],"which":[6,218],"social":[7,196],"interactions":[8],"happen,":[9],"and":[10,32,49,104,131,170],"can":[11,139,203,209],"be":[12],"measured":[13],"using":[14],"speech":[15],"audio":[16,179],"by":[17,200],"counting":[18],"number":[20],"of":[21,54,62,114,154,192],"concurrent":[22],"speakers.":[23],"This":[24],"measurement":[25],"has":[26],"enabled":[27],"various":[28,101],"mental":[29],"health":[30],"tracking":[31],"human-centric":[33],"IoT":[34],"applications.":[35],"While":[36],"on-device":[37,115,215],"Socal":[38],"Ambiance":[39],"Measure":[40],"(SAM)":[41],"is":[42,87],"highly":[43],"desirable":[44],"to":[45,94,100],"ensure":[46],"user":[47],"privacy":[48,102],"thus":[50],"facilitate":[51],"wide":[52],"adoption":[53],"aforementioned":[56],"applications,":[57],"required":[59,106],"computational":[60],"complexity":[61],"state-of-the-art":[63],"deep":[64],"neural":[65,125],"networks":[66],"(DNNs)":[67],"powered":[68],"SAM":[69,95,116,133,156,216],"solutions":[70,217],"stands":[71],"at":[72],"odds":[73],"with":[74],"often":[76],"constrained":[77],"resources":[78],"on":[79,181,194],"mobile":[80,155],"devices.":[81],"Furthermore,":[82],"only":[83,162,187],"limited":[84],"labeled":[85],"data":[86],"available":[88],"or":[89],"practical":[90],"when":[91],"it":[92],"comes":[93],"under":[96],"clinical":[97],"settings":[98],"due":[99],"constraints":[103],"human":[107],"effort,":[108],"further":[109],"challenging":[110],"achievable":[112,148],"accuracy":[113,149],"solutions.":[117,157],"To":[118],"this":[119],"end,":[120],"we":[121],"propose":[122],"a":[123,176,182,195],"dedicated":[124],"architecture":[126],"search":[127,141],"framework":[128,138,208],"for":[129,142,175,213],"Energy-efficient":[130],"Real-time":[132],"(ERSAM).":[134],"Specifically,":[135],"our":[136,206],"ERSAM":[137,207],"automatically":[140],"DNNs":[143,161],"that":[144,205],"push":[145],"forward":[146],"vs.":[150],"hardware":[151],"efficiency":[152],"frontier":[153],"For":[158],"example,":[159],"ERSAM-delivered":[160],"consume":[163],"40":[164],"mW":[165],"\u2022":[166],"12":[167],"h":[168],"energy":[169],"0.05":[171],"seconds":[172,178],"processing":[173],"latency":[174],"5":[177],"segment":[180],"Pixel":[183],"3":[184],"phone,":[185],"while":[186],"achieving":[188],"an":[189],"error":[190],"rate":[191],"14.3%":[193],"dataset":[198],"generated":[199],"LibriSpeech.":[201],"We":[202],"expect":[204],"pave":[210],"way":[212],"ubiquitous":[214],"are":[219],"growing":[221],"demand.":[222]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}