{"id":"https://openalex.org/W4406858451","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848599","title":"Real-Time Noise Estimation for Lombard-Effect Speech Synthesis in Human\u2013Avatar Dialogue Systems","display_name":"Real-Time Noise Estimation for Lombard-Effect Speech Synthesis in Human\u2013Avatar Dialogue Systems","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858451","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848599"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102633209","display_name":"Yuto Ishikawa","orcid":null},"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":true,"raw_author_name":"Yuto Ishikawa","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912590","display_name":"Osamu Take","orcid":null},"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":"Osamu Take","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["The National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051506797","display_name":"Norihiro Takamune","orcid":"https://orcid.org/0000-0002-8102-3110"},"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":"Norihiro Takamune","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"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":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"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":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102633209"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24343629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9925000071525574,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9925000071525574,"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/T13382","display_name":"Robotics and Automated Systems","score":0.986299991607666,"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/T10860","display_name":"Speech and Audio Processing","score":0.9472000002861023,"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/avatar","display_name":"Avatar","score":0.8356289863586426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540497779846191},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.672622799873352},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6139736771583557},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4825729429721832},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46884357929229736},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4578996002674103},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4372923970222473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30571597814559937},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.27083152532577515},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1524287760257721},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10109582543373108}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.8356289863586426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540497779846191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.672622799873352},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6139736771583557},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4825729429721832},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46884357929229736},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4578996002674103},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4372923970222473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30571597814559937},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27083152532577515},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1524287760257721},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10109582543373108},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":21,"referenced_works":["https://openalex.org/W1992475611","https://openalex.org/W2005785860","https://openalex.org/W2114461480","https://openalex.org/W2127851351","https://openalex.org/W2145563317","https://openalex.org/W2159485234","https://openalex.org/W2165430072","https://openalex.org/W2412956798","https://openalex.org/W2902884642","https://openalex.org/W2975911382","https://openalex.org/W3040525654","https://openalex.org/W3081800019","https://openalex.org/W3098557217","https://openalex.org/W4226031686","https://openalex.org/W4290742115","https://openalex.org/W4401609646","https://openalex.org/W4402111697","https://openalex.org/W6675349207","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106"],"abstract_inverted_index":{"To":[0],"facilitate":[1],"smooth":[2],"communication":[3],"between":[4],"a":[5,35],"human":[6],"(client)":[7],"and":[8,76,79,106],"an":[9],"avatar/robot,":[10],"it":[11],"is":[12,74],"essential":[13],"to":[14,68,89],"generate":[15],"avatar/robot":[16,65,91],"speech":[17,53,66],"that":[18,60,69,113],"reduces":[19],"the":[20,24,38,44,61,64,71,82,90,114],"listening":[21],"effort":[22],"for":[23,37],"client":[25],"in":[26,120],"noisy":[27,121],"acoustic":[28],"environments.":[29,122],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"framework":[36,95,116],"following":[39],"two":[40],"purposes":[41],"by":[42,85],"leveraging":[43],"estimated":[45,72],"noise":[46,73],"using":[47],"our":[48],"previously":[49],"proposed":[50,94,115],"real-time":[51,57],"blind":[52],"extraction":[54],"method:":[55],"(i)":[56],"adjustment":[58],"so":[59],"power":[62],"of":[63,70],"relative":[67],"constant":[75],"sufficiently":[77],"large,":[78],"(ii)":[80],"mimicking":[81],"Lombard":[83],"effect":[84],"simply":[86],"applying":[87],"filters":[88],"speech.":[92],"The":[93],"can":[96],"also":[97],"smoothly":[98],"connect":[99],"speeches":[100],"generated":[101],"from":[102],"voice":[103],"conversion":[104],"(avatar)":[105],"text-to-speech":[107],"(robot)":[108],"techniques.":[109],"Subjective":[110],"evaluations":[111],"demonstrated":[112],"achieves":[117],"natural":[118],"synthesis":[119]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
