{"id":"https://openalex.org/W4392904822","doi":"https://doi.org/10.1109/icassp48485.2024.10447696","title":"Iphonmatchnet: Zero-Shot User-Defined Keyword Spotting Using Implicit Acoustic Echo Cancellation","display_name":"Iphonmatchnet: Zero-Shot User-Defined Keyword Spotting Using Implicit Acoustic Echo Cancellation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904822","doi":"https://doi.org/10.1109/icassp48485.2024.10447696"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5030203043","display_name":"Yong-Hyeok Lee","orcid":"https://orcid.org/0000-0002-2972-9474"},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yong-Hyeok Lee","raw_affiliation_strings":["NCSOFT Corporation,Speech AI Lab., NC Research","Speech AI Lab., NC Research, NCSOFT Corporation"],"affiliations":[{"raw_affiliation_string":"NCSOFT Corporation,Speech AI Lab., NC Research","institution_ids":["https://openalex.org/I114129787"]},{"raw_affiliation_string":"Speech AI Lab., NC Research, NCSOFT Corporation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020960851","display_name":"Nam Hyun Cho","orcid":"https://orcid.org/0000-0002-7188-0565"},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Namhyun Cho","raw_affiliation_strings":["NCSOFT Corporation,Speech AI Lab., NC Research","Speech AI Lab., NC Research, NCSOFT Corporation"],"affiliations":[{"raw_affiliation_string":"NCSOFT Corporation,Speech AI Lab., NC Research","institution_ids":["https://openalex.org/I114129787"]},{"raw_affiliation_string":"Speech AI Lab., NC Research, NCSOFT Corporation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030203043"],"corresponding_institution_ids":["https://openalex.org/I114129787"],"apc_list":null,"apc_paid":null,"fwci":0.9877,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72146264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12642","last_page":"12646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8143037557601929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043956756591797},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.7970969676971436},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6553618907928467},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5409373641014099},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.535434365272522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.533654510974884},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.45184776186943054},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.441169798374176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2781863212585449},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0886458158493042}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8143037557601929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043956756591797},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.7970969676971436},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6553618907928467},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5409373641014099},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.535434365272522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.533654510974884},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.45184776186943054},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.441169798374176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2781863212585449},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0886458158493042},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W1535923754","https://openalex.org/W2061093115","https://openalex.org/W2078653151","https://openalex.org/W2136911347","https://openalex.org/W2219249508","https://openalex.org/W2763188033","https://openalex.org/W2797583228","https://openalex.org/W2963050656","https://openalex.org/W2972549707","https://openalex.org/W2973044449","https://openalex.org/W2973133192","https://openalex.org/W3008790380","https://openalex.org/W3015399080","https://openalex.org/W3160115460","https://openalex.org/W3160394811","https://openalex.org/W3162273446","https://openalex.org/W3216993959","https://openalex.org/W4224919230","https://openalex.org/W4283767777","https://openalex.org/W4372266577","https://openalex.org/W4385823483","https://openalex.org/W4392902956","https://openalex.org/W6688816777","https://openalex.org/W6750665317","https://openalex.org/W6757022092"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"In":[0],"response":[1],"to":[2,50,77,93],"the":[3,22,52,78,109],"increasing":[4],"interest":[5],"in":[6,64,72,115],"human\u2013machine":[7],"communication":[8],"across":[9],"various":[10],"domains,":[11],"this":[12],"paper":[13],"introduces":[14],"a":[15,37,60,69,99],"novel":[16],"approach":[17],"called":[18],"iPhonMatchNet,":[19],"which":[20],"addresses":[21],"challenge":[23],"of":[24,54,104,119],"barge-in":[25],"scenarios,":[26],"wherein":[27],"user":[28],"speech":[29],"overlaps":[30],"with":[31,68],"device":[32],"playback":[33],"audio,":[34],"thereby":[35],"creating":[36],"self-referencing":[38],"problem.":[39],"The":[40,102],"proposed":[41,110],"model":[42,73,87,111],"leverages":[43],"implicit":[44],"acoustic":[45],"echo":[46],"cancellation":[47],"(iAEC)":[48],"techniques":[49],"increase":[51,71],"efficiency":[53],"user-defined":[55],"keyword":[56],"spotting":[57],"models,":[58],"achieving":[59],"remarkable":[61],"95%":[62],"reduction":[63],"mean":[65],"absolute":[66],"error":[67],"minimal":[70],"size":[74],"(0.13%)":[75],"compared":[76],"baseline":[79],"model,":[80],"PhonMatchNet.":[81],"We":[82],"also":[83],"present":[84],"an":[85],"efficient":[86],"structure":[88],"and":[89],"demonstrate":[90],"its":[91],"capability":[92],"learn":[94],"iAEC":[95],"functionality":[96],"without":[97],"requiring":[98],"clean":[100],"signal.":[101],"findings":[103],"our":[105],"study":[106],"indicate":[107],"that":[108],"achieves":[112],"competitive":[113],"performance":[114],"real-world":[116],"deployment":[117],"conditions":[118],"smart":[120],"devices.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
