{"id":"https://openalex.org/W7131824155","doi":"https://doi.org/10.1109/sii64115.2026.11404612","title":"Speech Separation via Harmonic Suppression in Multi-Speaker Conversations to Assist Individuals with Hearing Loss","display_name":"Speech Separation via Harmonic Suppression in Multi-Speaker Conversations to Assist Individuals with Hearing Loss","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131824155","doi":"https://doi.org/10.1109/sii64115.2026.11404612"},"language":null,"primary_location":{"id":"doi:10.1109/sii64115.2026.11404612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","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/A5127300050","display_name":"Kai Ito","orcid":null},"institutions":[{"id":"https://openalex.org/I131231118","display_name":"Aoyama Gakuin University","ror":"https://ror.org/002rw7y37","country_code":"JP","type":"education","lineage":["https://openalex.org/I131231118"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kai Ito","raw_affiliation_strings":["Aoyama Gakuin University,Graduate School of Science and Technology,Kanagawa,Japan"],"affiliations":[{"raw_affiliation_string":"Aoyama Gakuin University,Graduate School of Science and Technology,Kanagawa,Japan","institution_ids":["https://openalex.org/I131231118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701798","display_name":"Yasuaki Ishikawa","orcid":"https://orcid.org/0000-0003-4613-6117"},"institutions":[{"id":"https://openalex.org/I131231118","display_name":"Aoyama Gakuin University","ror":"https://ror.org/002rw7y37","country_code":"JP","type":"education","lineage":["https://openalex.org/I131231118"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuaki Ishikawa","raw_affiliation_strings":["Aoyamagakuin University,School of Science and Technology,Department of Electrical Engineering and Electronics,Kanagawa,Japan"],"affiliations":[{"raw_affiliation_string":"Aoyamagakuin University,School of Science and Technology,Department of Electrical Engineering and Electronics,Kanagawa,Japan","institution_ids":["https://openalex.org/I131231118"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046358908","display_name":"Taku Itami","orcid":"https://orcid.org/0009-0007-4610-3207"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taku Itami","raw_affiliation_strings":["Meiji University,School of Science and Technology,Department of Electronics and Bioinfomatics,Kanagawa,Japan"],"affiliations":[{"raw_affiliation_string":"Meiji University,School of Science and Technology,Department of Electronics and Bioinfomatics,Kanagawa,Japan","institution_ids":["https://openalex.org/I16656306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5127300050"],"corresponding_institution_ids":["https://openalex.org/I131231118"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92937564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1186","last_page":"1191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5206999778747559,"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":0.5206999778747559,"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":0.17880000174045563,"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"}},{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.06159999966621399,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/separation","display_name":"Separation (statistics)","score":0.5490000247955322},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5160999894142151},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5156999826431274},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.5041999816894531},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4724000096321106},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4578999876976013},{"id":"https://openalex.org/keywords/hearing-aid","display_name":"Hearing aid","score":0.445499986410141},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4162999987602234}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.816100001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419000029563904},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.5041999816894531},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4578999876976013},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C3018256011","wikidata":"https://www.wikidata.org/wiki/Q898987","display_name":"Separation method","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2780493683","wikidata":"https://www.wikidata.org/wiki/Q16035842","display_name":"Hearing loss","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii64115.2026.11404612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4712691605091095}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2076422634","https://openalex.org/W2528970653","https://openalex.org/W2621984810","https://openalex.org/W3097643313","https://openalex.org/W3137585377","https://openalex.org/W3156681036","https://openalex.org/W4296068589","https://openalex.org/W4386763469","https://openalex.org/W4402407343"],"related_works":[],"abstract_inverted_index":{"It":[0],"is":[1,83],"difficult":[2],"for":[3],"deaf":[4],"and":[5,30,94,111,119],"hard-of-hearing":[6],"people":[7],"to":[8,56],"obtain":[9],"information":[10],"from":[11,66,90],"their":[12],"hearing,":[13],"particularly":[14],"in":[15,114],"group":[16],"conversations":[17],"where":[18],"multiple":[19],"speakers":[20],"overlap.":[21],"In":[22],"this":[23,81],"study,":[24],"we":[25,52],"propose":[26,53],"a":[27,38,54,67],"speech":[28,102,117],"separation":[29,118],"recognition":[31,97,103,120],"system":[32,82],"that":[33],"does":[34],"not":[35],"rely":[36],"on":[37,45],"deep":[39],"neural":[40],"network":[41],"but":[42],"instead":[43],"focuses":[44],"the":[46,58,64,73,76,91,96,108],"removal":[47],"of":[48,61,63,75,80,116],"harmonic":[49],"components.":[50],"Specifically,":[51],"method":[55,110],"extract":[57],"frequency":[59],"components":[60],"one":[62],"sounds":[65],"mixed-gender":[68],"audio":[69],"signal":[70,93],"by":[71,85],"removing":[72],"harmonics":[74],"other.":[77],"The":[78],"effectiveness":[79],"evaluated":[84],"separating":[86],"each":[87],"individual":[88],"voice":[89],"mixed":[92],"measuring":[95],"accuracy":[98],"using":[99],"an":[100],"automatic":[101],"(ASR)":[104],"system.":[105],"We":[106],"discuss":[107],"proposed":[109],"validation":[112],"results":[113],"terms":[115],"accuracy.":[121]},"counts_by_year":[],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2026-02-28T00:00:00"}