{"id":"https://openalex.org/W4405709843","doi":"https://doi.org/10.1109/iscslp63861.2024.10800089","title":"CATAD: Conformer-Based Adversarial Training with Adaptive Diffusion for Bone-Conducted Speech Enhancement","display_name":"CATAD: Conformer-Based Adversarial Training with Adaptive Diffusion for Bone-Conducted Speech Enhancement","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709843","doi":"https://doi.org/10.1109/iscslp63861.2024.10800089"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5084398453","display_name":"Zhiqiang Duan","orcid":"https://orcid.org/0009-0003-4097-4336"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiqiang Duan","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei"],"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002560091","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-6660-5190"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei"],"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei"],"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709936","display_name":"Liang Tao","orcid":"https://orcid.org/0000-0001-8553-8421"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Tao","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei"],"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578581","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0001-9727-366X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei"],"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computing,Hefei","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084398453"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27065375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9954000115394592,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9067000150680542,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6997625827789307},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6362465023994446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6009446978569031},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.503861129283905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3645986020565033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32255664467811584},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09963357448577881}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6997625827789307},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6362465023994446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6009446978569031},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.503861129283905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3645986020565033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32255664467811584},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09963357448577881},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1996838623","display_name":null,"funder_award_id":"62201002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8673086302","display_name":null,"funder_award_id":"1908085MF209","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1989337816","https://openalex.org/W1991590998","https://openalex.org/W2021087336","https://openalex.org/W2056852181","https://openalex.org/W2125114513","https://openalex.org/W2133765057","https://openalex.org/W2137793486","https://openalex.org/W2141998673","https://openalex.org/W2149649354","https://openalex.org/W2809941692","https://openalex.org/W2937484199","https://openalex.org/W2965825901","https://openalex.org/W2995343943","https://openalex.org/W3011318140","https://openalex.org/W3015197852","https://openalex.org/W3093686966","https://openalex.org/W3097777922","https://openalex.org/W3163842642","https://openalex.org/W4200628964","https://openalex.org/W4224883138","https://openalex.org/W4312068791","https://openalex.org/W4312469383","https://openalex.org/W4323854608","https://openalex.org/W4389164214","https://openalex.org/W4395447416","https://openalex.org/W6713394505"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Due":[0],"to":[1,67,101,119],"the":[2,8,69,76,79,84,87,102,114,117,132,137],"low-pass":[3],"filtering":[4],"of":[5,11,56,71,78,86,116,154],"human":[6],"tissues,":[7],"high-frequency":[9],"components":[10,144],"bone-conducted":[12,46],"(BC)":[13],"speech":[14,21,47,72,124,150],"suffer":[15],"severe":[16],"attenuation,":[17],"resulting":[18],"in":[19],"reduced":[20],"quality":[22],"and":[23,63,83,104,125,152],"intelligibility.":[24],"To":[25,74],"address":[26],"this":[27,29],"issue,":[28],"paper":[30],"proposes":[31],"a":[32,53],"novel":[33],"approach":[34],"called":[35],"CATAD,":[36,50],"which":[37],"employs":[38],"conformer-based":[39],"adversarial":[40,80],"training":[41],"with":[42],"adaptive":[43,93,110],"diffusion":[44,94,111],"for":[45],"enhancement.":[48],"In":[49],"we":[51,90],"deploy":[52],"TS-Conformer":[54],"consisting":[55],"two":[57],"Conformer":[58],"modules":[59],"that":[60,136],"capture":[61],"temporal":[62],"frequency":[64],"dependencies,":[65],"respectively,":[66],"enhance":[68],"expressiveness":[70],"features.":[73],"ensure":[75],"stability":[77],"learning":[81],"process":[82,95,112],"diversity":[85],"generated":[88,103],"results,":[89],"adopt":[91],"an":[92],"where":[96],"random":[97],"noise":[98],"is":[99],"added":[100],"real":[105,122],"data,":[106],"respectively.":[107],"The":[108],"proposed":[109,138],"boosts":[113],"capability":[115],"discriminator":[118],"distinguish":[120],"between":[121],"air-conducted":[123],"enhanced":[126],"BC":[127,146,155],"speech.":[128,156],"Experimental":[129],"results":[130],"on":[131],"ESMB":[133],"dataset":[134],"demonstrate":[135],"CATAD":[139],"can":[140],"recover":[141],"absent":[142],"high":[143],"from":[145],"speech,":[147],"substantially":[148],"improving":[149],"quaility":[151],"intelligiblity":[153]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
