{"id":"https://openalex.org/W4372271592","doi":"https://doi.org/10.1109/icassp49357.2023.10094788","title":"HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones","display_name":"HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372271592","doi":"https://doi.org/10.1109/icassp49357.2023.10094788"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094788","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/A5070899335","display_name":"N Shashaank","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N Shashaank","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA","Department of Computer Science, Columbia University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Department of Computer Science, Columbia University, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090034492","display_name":"Berker Banar","orcid":"https://orcid.org/0000-0003-1808-2203"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Berker Banar","raw_affiliation_strings":["Bose Corporation,MA,USA","School of Electronic Engineering and Computer Science, Queen Mary University of London, UK","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033902274","display_name":"Mohammad Izadi","orcid":"https://orcid.org/0000-0003-3561-3942"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Rasool Izadi","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016664686","display_name":"Jeremy P. Kemmerer","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Kemmerer","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450332","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0001-5197-6028"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085831884","display_name":"Chuan-Che Jeff Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuan-Che Jeff Huang","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61464653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/headphones","display_name":"Headphones","score":0.9322720766067505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852128744125366},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5332417488098145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5292108654975891},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41617900133132935},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41282233595848083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.306377649307251},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09454867243766785}],"concepts":[{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.9322720766067505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852128744125366},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5332417488098145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5292108654975891},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41617900133132935},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41282233595848083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.306377649307251},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09454867243766785},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094788","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W2017310186","https://openalex.org/W2052666245","https://openalex.org/W2094721231","https://openalex.org/W2539062311","https://openalex.org/W2566935005","https://openalex.org/W2601450892","https://openalex.org/W2941163248","https://openalex.org/W2963163009","https://openalex.org/W2982341288","https://openalex.org/W3013020904","https://openalex.org/W3015474227","https://openalex.org/W3015594652","https://openalex.org/W3203242999","https://openalex.org/W4205689591","https://openalex.org/W4220871331","https://openalex.org/W4287077834","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6735236233","https://openalex.org/W6798064515"],"related_works":["https://openalex.org/W1519334917","https://openalex.org/W2285322832","https://openalex.org/W2069110031","https://openalex.org/W2511793349","https://openalex.org/W2506159889","https://openalex.org/W4237416696","https://openalex.org/W2293832935","https://openalex.org/W2968763213","https://openalex.org/W2037844040","https://openalex.org/W4387872898"],"abstract_inverted_index":{"Modern":[0],"noise-cancelling":[1],"headphones":[2,40,118],"have":[3,109],"significantly":[4],"improved":[5],"users\u2019":[6],"auditory":[7],"experiences":[8],"by":[9,181],"removing":[10],"unwanted":[11],"background":[12],"noise,":[13],"but":[14],"they":[15],"can":[16,38],"also":[17],"block":[18],"out":[19,76],"sounds":[20,92,158],"that":[21,93,146,170],"matter":[22],"to":[23,41,86,96,114,152,187,210],"users.":[24],"Machine":[25],"learning":[26],"(ML)":[27],"models":[28,50,82,107,190],"for":[29,51,193],"sound":[30,70],"event":[31],"detection":[32,71],"(SED)":[33],"and":[34,102,135,143,156,161,165],"speaker":[35],"identification":[36],"(SID)":[37],"enable":[39],"selectively":[42],"pass":[43],"through":[44],"important":[45,95],"sounds;":[46],"however,":[47],"implementing":[48],"these":[49,129],"a":[52,110,148],"user-centric":[53],"experience":[54],"presents":[55],"several":[56],"unique":[57],"challenges.":[58],"First,":[59],"most":[60],"people":[61],"spend":[62],"limited":[63,120],"time":[64,89],"customizing":[65],"their":[66,100],"headphones,":[67],"so":[68],"the":[69,78,81,90,206],"should":[72,83,108],"work":[73],"reasonably":[74],"well":[75],"of":[77,159],"box.":[79],"Second,":[80],"be":[84],"able":[85],"learn":[87],"over":[88],"specific":[91,157],"are":[94],"users":[97],"based":[98],"on":[99,116],"implicit":[101],"explicit":[103],"interactions.":[104],"Finally,":[105],"such":[106],"small":[111],"memory":[112,207],"footprint":[113,208],"run":[115],"low-power":[117],"with":[119],"on-chip":[121],"memory.":[122],"In":[123],"this":[124],"paper,":[125],"we":[126],"propose":[127],"addressing":[128],"challenges":[130],"using":[131,177],"HiSSNet":[132,138,171,198],"(Hierarchical":[133],"SED":[134,194],"SID":[136,196],"Network).":[137],"is":[139],"an":[140,173],"SEID":[141,174],"(SED":[142],"SID)":[144],"model":[145,175],"uses":[147],"hierarchical":[149],"prototypical":[150,179],"network":[151],"detect":[153],"both":[154,163],"general":[155],"interest":[160],"characterize":[162],"alarm-like":[164],"speech":[166],"sounds.":[167],"We":[168],"show":[169],"outperforms":[172],"trained":[176,191],"non-hierarchical":[178],"networks":[180],"6.9":[182],"\u2013":[183],"8.6%.":[184],"When":[185],"compared":[186],"state-of-the-art":[188],"(SOTA)":[189],"specifically":[192],"or":[195,201],"alone,":[197],"achieves":[199],"similar":[200],"better":[202],"performance":[203],"while":[204],"reducing":[205],"required":[209],"support":[211],"multiple":[212],"capabilities":[213],"on-device.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-05-07T00:00:00"}
