{"id":"https://openalex.org/W4402349786","doi":"https://doi.org/10.1145/3678594","title":"EarSpeech: Exploring In-Ear Occlusion Effect on Earphones for Data-efficient Airborne Speech Enhancement","display_name":"EarSpeech: Exploring In-Ear Occlusion Effect on Earphones for Data-efficient Airborne Speech Enhancement","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4402349786","doi":"https://doi.org/10.1145/3678594"},"language":"en","primary_location":{"id":"doi:10.1145/3678594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678594","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-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/A5006962629","display_name":"Feiyu Han","orcid":"https://orcid.org/0000-0002-7555-1232"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Han","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China and University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7555-1232","affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China and University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I200845125","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087967463","display_name":"Panlong Yang","orcid":"https://orcid.org/0000-0003-1057-2793"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panlong Yang","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1057-2793","affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111319696","display_name":"You Zuo","orcid":"https://orcid.org/0009-0004-0769-2924"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Zuo","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0004-0769-2924","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812009","display_name":"Fei Shang","orcid":"https://orcid.org/0000-0002-5495-8869"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Shang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5495-8869","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045605868","display_name":"Fenglei Xu","orcid":"https://orcid.org/0000-0002-5454-157X"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenglei Xu","raw_affiliation_strings":["Suzhou University of Science and Technology, Jiangsu Industrial Intelligent and Low-carbon Technology Engineering Center, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5454-157X","affiliations":[{"raw_affiliation_string":"Suzhou University of Science and Technology, Jiangsu Industrial Intelligent and Low-carbon Technology Engineering Center, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341802","display_name":"Xiang\u2010Yang Li","orcid":"https://orcid.org/0000-0002-6070-6625"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang-Yang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6070-6625","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8154,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.917451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"8","issue":"3","first_page":"1","last_page":"30"},"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":0.9990000128746033,"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":0.9973000288009644,"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":0.7708373069763184},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.74601811170578},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6612628698348999},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5752848982810974},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5477790236473083},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5473898649215698},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4474659562110901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2629856467247009},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2535717189311981},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10642990469932556},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09845978021621704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708373069763184},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.74601811170578},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6612628698348999},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5752848982810974},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5477790236473083},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5473898649215698},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4474659562110901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2629856467247009},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2535717189311981},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10642990469932556},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09845978021621704},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678594","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5717137518","display_name":null,"funder_award_id":"No. 62072004","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W2051057783","https://openalex.org/W2052666245","https://openalex.org/W2075794890","https://openalex.org/W2096779346","https://openalex.org/W2120605154","https://openalex.org/W2144370544","https://openalex.org/W2304609584","https://openalex.org/W2790428568","https://openalex.org/W2894651928","https://openalex.org/W2937484199","https://openalex.org/W2940177920","https://openalex.org/W2953297989","https://openalex.org/W2963828919","https://openalex.org/W2992628507","https://openalex.org/W2998161426","https://openalex.org/W3025051662","https://openalex.org/W3129328687","https://openalex.org/W3136499730","https://openalex.org/W3140645045","https://openalex.org/W3153632018","https://openalex.org/W3175702010","https://openalex.org/W3195180329","https://openalex.org/W3198130403","https://openalex.org/W3199910673","https://openalex.org/W3205995231","https://openalex.org/W3213319487","https://openalex.org/W4200186631","https://openalex.org/W4236965008","https://openalex.org/W4283031696","https://openalex.org/W4283219085","https://openalex.org/W4288062117","https://openalex.org/W4294892047","https://openalex.org/W4297095639","https://openalex.org/W4311187069","https://openalex.org/W4317927963","https://openalex.org/W4322731291","https://openalex.org/W4323854608","https://openalex.org/W4366581013","https://openalex.org/W4380928279","https://openalex.org/W4386699348","https://openalex.org/W4387212420","https://openalex.org/W4402349786","https://openalex.org/W4404173033"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Earphones":[0],"have":[1],"become":[2],"a":[3,86,144,215],"popular":[4],"voice":[5],"input":[6],"and":[7,25,40,84,123,130,154,163,189,195,198,238],"interaction":[8],"device.":[9],"However,":[10,91],"airborne":[11,66,89,110],"speech":[12,28,67,77,98,139,236],"is":[13,74,78,219,258],"susceptible":[14],"to":[15,21,64,81,93,105,118,133,158,173],"ambient":[16,82],"noise,":[17],"making":[18,102],"it":[19,103],"necessary":[20],"improve":[22,159],"the":[23,35,61,94,115,160,175,224,231,247],"quality":[24],"intelligibility":[26],"of":[27,72,126,146,165,177,187,193,233,256],"on":[29,260],"earphones":[30,48],"in":[31,47,191,246],"noisy":[32],"conditions.":[33],"As":[34],"dual-microphone":[36],"structure":[37],"(i.e.,":[38],"outer":[39],"in-ear":[41,57,76,97],"microphones)":[42],"has":[43,99],"been":[44],"widely":[45],"adopted":[46],"(especially":[49],"ANC":[50],"earphones),":[51],"we":[52,113,142,169,229],"design":[53,143],"EarSpeech":[54,73,181,209,257],"which":[55],"exploits":[56],"acoustic":[58],"sensory":[59],"as":[60,242,244],"complementary":[62],"modality":[63],"enable":[65],"enhancement.":[68,140],"The":[69,253],"key":[70],"idea":[71],"that":[75,218],"less":[79,222],"sensitive":[80],"noise":[83,155],"exhibits":[85],"correlation":[87,129,137],"with":[88,108,214],"speech.":[90,111],"due":[92],"occlusion":[95,116],"effect,":[96],"limited":[100],"bandwidth,":[101],"challenging":[104],"directly":[106],"correlate":[107],"full-band":[109],"Therefore,":[112],"exploit":[114],"effect":[117],"carry":[119],"out":[120],"theoretical":[121],"modeling":[122],"quantitative":[124],"analysis":[125],"this":[127],"cross-channel":[128,136],"study":[131],"how":[132],"leverage":[134],"such":[135],"for":[138],"Specifically,":[141,180],"series":[145],"methodologies":[147],"including":[148],"data":[149,207],"augmentation,":[150,208],"deep":[151],"learning-based":[152],"fusion,":[153],"mixture":[156],"scheme,":[157],"generalization,":[161],"effectiveness,":[162],"robustness":[164,245],"EarSpeech,":[166],"respectively.":[167],"Lastly,":[168],"conduct":[170],"real-world":[171],"experiments":[172],"evaluate":[174],"performance":[176,213],"our":[178],"system.":[179],"achieves":[182],"an":[183],"average":[184],"improvement":[185],"ratio":[186],"27.23%":[188],"13.92%":[190],"terms":[192],"PESQ":[194],"STOI,":[196],"respectively,":[197,241],"significantly":[199],"improves":[200],"SI-SDR":[201],"by":[202],"8.91":[203],"dB.":[204],"Benefiting":[205],"from":[206],"can":[210],"achieve":[211],"comparable":[212],"small-scale":[216],"dataset":[217],"40":[220],"times":[221],"than":[223],"original":[225],"dataset.":[226],"In":[227],"addition,":[228],"validate":[230],"generalization":[232],"different":[234],"users,":[235],"content,":[237],"language":[239],"types,":[240],"well":[243],"real":[248],"world":[249],"via":[250],"comprehensive":[251],"experiments.":[252],"audio":[254],"demo":[255],"available":[259],"https://github.com/EarSpeech/earspeech.github.io/.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
