{"id":"https://openalex.org/W4408353968","doi":"https://doi.org/10.1109/icassp49660.2025.10888094","title":"Robust Fusion of Bone and Air-Conducted Sensors for Speech Enhancement with Adaptive Temporal-Frequency Attention","display_name":"Robust Fusion of Bone and Air-Conducted Sensors for Speech Enhancement with Adaptive Temporal-Frequency Attention","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353968","doi":"https://doi.org/10.1109/icassp49660.2025.10888094"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5050869508","display_name":"Zhenglong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenglong Liu","raw_affiliation_strings":["Dalian University of,School of Information and Communication Engineering,Technology,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of,School of Information and Communication Engineering,Technology,China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783392","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0002-6822-9667"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["Dalian University of,School of Information and Communication Engineering,Technology,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of,School of Information and Communication Engineering,Technology,China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080791396","display_name":"Fuliang Yin","orcid":"https://orcid.org/0000-0003-2642-8489"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuliang Yin","raw_affiliation_strings":["Dalian University of,School of Information and Communication Engineering,Technology,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of,School of Information and Communication Engineering,Technology,China","institution_ids":["https://openalex.org/I4210092944"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050869508"],"corresponding_institution_ids":["https://openalex.org/I4210092944"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75614251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9835000038146973,"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":0.9835000038146973,"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":0.9205999970436096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6214762926101685},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.511326014995575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5060126185417175},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5051451325416565},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.42889225482940674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2846224308013916},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.05864995718002319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6214762926101685},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.511326014995575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5060126185417175},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5051451325416565},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.42889225482940674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2846224308013916},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.05864995718002319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W95300890","https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W2128127640","https://openalex.org/W2141998673","https://openalex.org/W2160450507","https://openalex.org/W2785898612","https://openalex.org/W2937977811","https://openalex.org/W2991251958","https://openalex.org/W2995201943","https://openalex.org/W2998445964","https://openalex.org/W3015199127","https://openalex.org/W3015219411","https://openalex.org/W3096408984","https://openalex.org/W3162341667","https://openalex.org/W3197627016","https://openalex.org/W3206809722","https://openalex.org/W4224931274","https://openalex.org/W4289716422","https://openalex.org/W4290713716","https://openalex.org/W4293527381","https://openalex.org/W4297095639","https://openalex.org/W4304979274","https://openalex.org/W4385245566","https://openalex.org/W4391873121","https://openalex.org/W4400490072","https://openalex.org/W6631190155","https://openalex.org/W6675344567"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2152662039"],"abstract_inverted_index":{"The":[0,128],"multi-modal":[1],"speech":[2,41],"enhancement":[3,43],"method":[4,44,164],"has":[5],"improved":[6],"performance":[7],"due":[8],"to":[9,88,125,138,155],"the":[10,48,61,68,83,90,95,111,118,126,140,149,153,157,162,171],"diverse":[11],"sources":[12],"of":[13,30,146,151,173],"its":[14],"input":[15,178],"data,":[16],"which":[17,82],"includes":[18],"low-distortion":[19],"air-conducted":[20],"(AC)":[21],"signals":[22,70,120],"and":[23,39,50,71,97,108,114,123],"low-noise":[24],"bone-conducted":[25],"(BC)":[26],"signals.":[27],"In":[28],"light":[29],"these":[31],"considerations,":[32],"a":[33,56,144],"novel":[34],"complex-domain":[35],"deep":[36],"learning-based":[37],"BC":[38,49,113],"AC":[40,51,115],"fusion":[42,167],"is":[45,53,65,86,136],"proposed.":[46],"Specifically,":[47],"spectrum":[52],"fed":[54,72],"into":[55,73],"pre-fusion":[57],"module":[58],"firstly.":[59],"Then":[60],"preliminary":[62],"fused":[63],"feature":[64],"concatenated":[66],"with":[67,110],"original":[69,112],"encoder,":[74],"followed":[75],"by":[76,106,142],"adaptive":[77],"time-frequency":[78],"attention":[79],"modules,":[80],"in":[81,93,148,170],"self-attention":[84],"mechanism":[85],"employed":[87],"reconstruct":[89],"encoded":[91],"features":[92],"both":[94],"time":[96],"frequency":[98],"axes.":[99],"After":[100],"that,":[101],"two":[102,119],"masks":[103],"are":[104,121],"generated":[105],"decoders":[107],"multiplied":[109],"spectrum.":[116],"Finally,":[117],"summed":[122],"converted":[124],"time-domain.":[127],"disabled":[129],"situation":[130],"when":[131],"only":[132],"one":[133,176],"sensor":[134],"works":[135],"considered":[137],"improve":[139],"robustness":[141,174],"introducing":[143],"probability":[145],"failure":[147],"process":[150],"feeding":[152],"data":[154],"train":[156],"model.":[158],"Experiments":[159],"demonstrate":[160],"that":[161],"proposed":[163],"outperforms":[165],"existing":[166],"approaches,":[168],"especially":[169],"aspect":[172],"against":[175],"invalid":[177],"channel.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}