{"id":"https://openalex.org/W4414348461","doi":"https://doi.org/10.1109/access.2025.3612004","title":"SilentWhisper: Enabling User-Independent Ultra-Low Volume Whispered Speech Recognition","display_name":"SilentWhisper: Enabling User-Independent Ultra-Low Volume Whispered Speech Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414348461","doi":"https://doi.org/10.1109/access.2025.3612004"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3612004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3612004","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3612004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052724008","display_name":"Hirotaka Hiraki","orcid":"https://orcid.org/0000-0002-6543-4593"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirotaka Hiraki","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan","The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6543-4593","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082649952","display_name":"Jun Rekimoto","orcid":"https://orcid.org/0000-0002-3629-2514"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Rekimoto","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan","The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27870535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"168782","last_page":"168791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9878000020980835,"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":0.9878000020980835,"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":0.9825999736785889,"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/T11309","display_name":"Music and Audio Processing","score":0.9165999889373779,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5163000226020813},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5162000060081482},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5055000185966492},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47269999980926514},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45989999175071716},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42309999465942383},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41429999470710754},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.37389999628067017},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36739999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382999897003174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7319999933242798},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5163000226020813},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.34709998965263367},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3125},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2581000030040741},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3612004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3612004","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bb182559969d47efa40905a2fb8d9446","is_oa":true,"landing_page_url":"https://doaj.org/article/bb182559969d47efa40905a2fb8d9446","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 168782-168791 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3612004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3612004","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2208446484","display_name":null,"funder_award_id":"JPNP23025","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"},{"id":"https://openalex.org/G2753022850","display_name":"\u5bfe\u9762\u3067\u306e\u767a\u58f0\u3092\u62e1\u5f35\u3067\u304d\u308b\u30a6\u30a7\u30a2\u30e9\u30d6\u30eb\u306a\u97f3\u58f0\u5165\u51fa\u529b\u30a4\u30f3\u30bf\u30d5\u30a7\u30fc\u30b9\u306e\u958b\u767a","funder_award_id":"JPMJAX23KG","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1995624940","https://openalex.org/W2008120082","https://openalex.org/W2011440797","https://openalex.org/W2022047569","https://openalex.org/W2047892947","https://openalex.org/W2051626970","https://openalex.org/W2066502876","https://openalex.org/W2087484885","https://openalex.org/W2120549061","https://openalex.org/W2160130475","https://openalex.org/W2160800342","https://openalex.org/W2526966955","https://openalex.org/W2768731046","https://openalex.org/W2770785043","https://openalex.org/W2793257307","https://openalex.org/W2806172474","https://openalex.org/W2896622783","https://openalex.org/W2897318954","https://openalex.org/W2921295135","https://openalex.org/W2941048526","https://openalex.org/W2973031936","https://openalex.org/W2980880049","https://openalex.org/W2996107505","https://openalex.org/W3010673682","https://openalex.org/W3083438180","https://openalex.org/W3083703874","https://openalex.org/W3091762102","https://openalex.org/W3132560018","https://openalex.org/W3144915432","https://openalex.org/W3160728073","https://openalex.org/W3160833628","https://openalex.org/W3161865163","https://openalex.org/W3163934237","https://openalex.org/W4205974199","https://openalex.org/W4294891788","https://openalex.org/W4321009928","https://openalex.org/W4391021791","https://openalex.org/W4396832598","https://openalex.org/W4396832776","https://openalex.org/W4396833340","https://openalex.org/W4396833564","https://openalex.org/W4396919354"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"Silent":[1],"Speech":[2],"Interfaces":[3],"(SSIs),":[4],"which":[5,83],"enable":[6],"private":[7,141],"voice":[8],"input,":[9],"are":[10],"often":[11],"hampered":[12],"by":[13],"user":[14],"dependency—a":[15],"critical":[16],"barrier":[17],"requiring":[18],"extensive":[19],"training":[20],"data":[21],"from":[22,95],"each":[23],"individual.":[24],"To":[25],"address":[26],"this,":[27],"we":[28],"propose":[29],"SilentWhisper,":[30],"a":[31,50,56,85,127,135,139],"system":[32,66],"that":[33,144],"achieves":[34],"truly":[35],"user-independent":[36,74],"recognition":[37,53],"of":[38],"ultra-low":[39],"volume":[40],"(45-50dB)":[41],"whispered":[42],"speech":[43,52],"using":[44],"only":[45],"standard":[46],"microphones.":[47],"By":[48],"fine-tuning":[49,105],"pre-trained":[51],"model":[54,110],"on":[55,118,126],"multi-user":[57],"dataset,":[58],"our":[59,73,130],"method":[60],"allows":[61],"anyone":[62],"to":[63,97,114,147],"use":[64],"the":[65,89,109,115],"immediately":[67],"without":[68],"per-user":[69],"adaptation.":[70],"We":[71],"validate":[72],"claim":[75],"through":[76],"rigorous":[77],"leave-one-out":[78],"cross-validation":[79],"with":[80],"13":[81],"participants,":[82],"confirmed":[84],"significant":[86,136],"reduction":[87],"in":[88],"average":[90],"Character":[91],"Error":[92],"Rate":[93],"(CER)":[94],"17.0%":[96],"7.3%":[98],"(a":[99],"57.1%":[100],"improvement).":[101],"Crucially,":[102],"this":[103],"specialized":[104],"is":[106,145],"also":[107],"robust;":[108],"maintains":[111],"performance":[112,133],"comparable":[113],"powerful":[116],"baseline":[117],"unseen":[119],"texts,":[120],"thus":[121],"avoiding":[122],"catastrophic":[123],"forgetting.":[124],"Evaluated":[125],"1,002-word":[128],"vocabulary,":[129],"system’s":[131],"strong":[132],"represents":[134],"step":[137],"towards":[138],"practical,":[140],"conversational":[142],"interface":[143],"accessible":[146],"all.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}