{"id":"https://openalex.org/W7148592424","doi":"https://doi.org/10.1109/asru65441.2025.11434754","title":"Speech Masking System Based on Spatially Separated Multiple TTS Maskers With A Compact Circular Loudspeaker Array","display_name":"Speech Masking System Based on Spatially Separated Multiple TTS Maskers With A Compact Circular Loudspeaker Array","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148592424","doi":"https://doi.org/10.1109/asru65441.2025.11434754"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132826953","display_name":"Takuma Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5132826953"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":1.4346,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87384331,"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":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6890000104904175,"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":0.6890000104904175,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.11940000206232071,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.012799999676644802,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.6409000158309937},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5289000272750854},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3066999912261963},{"id":"https://openalex.org/keywords/auditory-masking","display_name":"Auditory masking","score":0.2671000063419342},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.2597000002861023}],"concepts":[{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.538100004196167},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5289000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5026999711990356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49559998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2797999978065491},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2533000111579895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1969105061","https://openalex.org/W1991631228","https://openalex.org/W2027599196","https://openalex.org/W2042293490","https://openalex.org/W2045461458","https://openalex.org/W2050628660","https://openalex.org/W2052666245","https://openalex.org/W2077250325","https://openalex.org/W2079604471","https://openalex.org/W2177310552","https://openalex.org/W2600995709","https://openalex.org/W2610770404","https://openalex.org/W2747070883","https://openalex.org/W2793325839","https://openalex.org/W2979794411","https://openalex.org/W2991264830","https://openalex.org/W3017134929","https://openalex.org/W3097777922","https://openalex.org/W3127950645","https://openalex.org/W3163793923","https://openalex.org/W4200268817","https://openalex.org/W4206787216","https://openalex.org/W4224283535","https://openalex.org/W4224612669","https://openalex.org/W4250500702","https://openalex.org/W4312242700","https://openalex.org/W4312443924","https://openalex.org/W4385823191","https://openalex.org/W4389228106","https://openalex.org/W4391892412","https://openalex.org/W4392903256","https://openalex.org/W4402112526","https://openalex.org/W4411949025","https://openalex.org/W7148400581"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"masking":[1,110,132],"system":[2,112,133],"with":[3,45,60,113,123,134],"spatially":[4,135],"separated":[5,136],"maskers":[6,44,67,94,139],"is":[7,140],"proposed":[8,41,130],"by":[9,55,70],"utilizing":[10],"multiple":[11,71,76,91,137],"sound":[12,72],"spot":[13,73],"synthesis":[14,74],"and":[15],"multi-speaker":[16,56],"neural":[17,57],"text-to-speech":[18],"(TTS)":[19],"technologies.":[20],"Although":[21],"previous":[22],"systems":[23],"introduce":[24],"time-reversed":[25],"signals":[26],"of":[27,118],"target":[28,52,80,88],"speech":[29,53,81,109,131],"for":[30],"maskers,":[31],"these":[32,65],"meaningless":[33],"sounds":[34],"are":[35,68],"unpleasant":[36],"to":[37],"listeners.":[38],"Conversely,":[39],"the":[40,46,79,87,101,127,129],"method":[42],"introduces":[43],"same":[47],"voice":[48],"quality":[49],"as":[50],"a":[51,108,114,124],"generated":[54],"TTS":[58],"model":[59],"global":[61],"style":[62],"tokens.":[63],"Additionally,":[64],"TTS-based":[66,92,138],"synthesized":[69],"in":[75],"directions.":[77],"Then,":[78],"can":[82,95],"only":[83],"be":[84,97],"heard":[85,99],"at":[86,100],"direction":[89],"while":[90],"meaningful":[93],"also":[96],"easily":[98],"other":[102],"directions":[103],"without":[104],"discomfort.":[105],"We":[106],"implement":[107],"demo":[111],"compact":[115],"circular":[116],"array":[117],"16":[119],"loudspeakers":[120],"carried":[121],"out":[122],"backpack.":[125],"In":[126],"demonstration,":[128],"demonstrated.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}