{"id":"https://openalex.org/W4408354639","doi":"https://doi.org/10.1109/icassp49660.2025.10889416","title":"Bone Conducted Signal Guided Speech Enhancement For Voice Assistant on Earbuds","display_name":"Bone Conducted Signal Guided Speech Enhancement For Voice Assistant on Earbuds","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354639","doi":"https://doi.org/10.1109/icassp49660.2025.10889416"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5021547071","display_name":"Jens Heitkaemper","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jens Heitkaemper","raw_affiliation_strings":["Google LLC,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060736846","display_name":"Joe Caroselli","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joe Caroselli","raw_affiliation_strings":["Google LLC,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594509","display_name":"Max McKinnon","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max McKinnon","raw_affiliation_strings":["Google LLC,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google LLC,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109115612","display_name":"Nathan Howard","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Howard","raw_affiliation_strings":["Google LLC,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021547071"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.2656,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76351983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9549999833106995,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9408000111579895,"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/computer-science","display_name":"Computer science","score":0.6834025382995605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6527251601219177},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.495456337928772},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4593003988265991},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.449171781539917},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44868409633636475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1588495373725891},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08147889375686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834025382995605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6527251601219177},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.495456337928772},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4593003988265991},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.449171781539917},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44868409633636475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1588495373725891},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08147889375686646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1544785557","https://openalex.org/W1597121597","https://openalex.org/W2040214655","https://openalex.org/W2156676906","https://openalex.org/W2593658960","https://openalex.org/W2617258110","https://openalex.org/W2951130829","https://openalex.org/W2964058413","https://openalex.org/W2973062255","https://openalex.org/W2991251958","https://openalex.org/W3015312544","https://openalex.org/W3015843733","https://openalex.org/W3083533149","https://openalex.org/W3083711808","https://openalex.org/W3162646409","https://openalex.org/W3198442913","https://openalex.org/W4297095639","https://openalex.org/W4304979274","https://openalex.org/W4311897894","https://openalex.org/W4319862426","https://openalex.org/W4327992672","https://openalex.org/W4372346318","https://openalex.org/W4380928279","https://openalex.org/W4391092659","https://openalex.org/W4402117038","https://openalex.org/W4409593739","https://openalex.org/W6713394505"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2051376034","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0,149],"this":[1],"work":[2],"we":[3],"present":[4],"a":[5,25,45,52,59,83,152],"multi-modal,":[6],"streaming":[7],"enhancement":[8,48,78,156],"network":[9],"to":[10,30,87,99,103,115,124,138],"improve":[11],"speech":[12,47,95],"recognition":[13,126],"for":[14,74,92,105],"voice":[15,84],"assistants":[16],"on":[17,44,58,168],"earbuds.":[18],"The":[19,128],"proposed":[20],"model":[21,43],"is":[22,80,113],"guided":[23],"by":[24,82],"bone":[26,111],"conducted":[27],"signal":[28],"(BCS)":[29],"separate":[31],"the":[32,36,42,77,89,101,106,110,117,122,125,132,158,171],"interfering":[33],"sources":[34],"from":[35,121],"target":[37],"speaker":[38],"signal.":[39],"We":[40],"train":[41],"simulated":[46,53],"training":[49,63],"set":[50],"with":[51,141,151,160],"BCS":[54,76,93,102,133],"and":[55,161],"finetune":[56],"it":[57],"small":[60,143],"earbuds":[61,123],"specific":[62],"set,":[64],"consisting":[65],"of":[66,70,109,170],"about":[67],"6":[68],"hours":[69],"speech.":[71],"To":[72],"account":[73,104],"distorted":[75],"module":[79],"complemented":[81],"activity-based":[85],"decision":[86],"discard":[88],"enhanced":[90],"output":[91],"without":[94,162],"information.":[96],"A":[97],"possibility":[98],"preprocess":[100],"low-pass":[107],"characteristic":[108],"conduction":[112],"evaluated":[114],"lower":[116],"required":[118],"transmission":[119],"bandwidth":[120,134,163],"device.":[127],"results":[129],"show":[130],"that":[131],"can":[135],"be":[136],"reduced":[137],"500":[139],"Hz":[140],"only":[142],"losses":[144],"in":[145],"word":[146],"error":[147],"rate.":[148],"comparison":[150],"larger":[153],"state-of-the-art":[154],"multi-channel":[155],"method,":[157],"systems,":[159],"reduction,":[164],"demonstrate":[165],"superior":[166],"performance":[167],"most":[169],"considered":[172],"realistic":[173],"test":[174],"sets.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}