{"id":"https://openalex.org/W4408345784","doi":"https://doi.org/10.1109/icassp49660.2025.10889321","title":"Multi-modal Speech Enhancement with Limited Electromyography Channels","display_name":"Multi-modal Speech Enhancement with Limited Electromyography Channels","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345784","doi":"https://doi.org/10.1109/icassp49660.2025.10889321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889321","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":null,"display_name":"Fuyuan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyuan Feng","raw_affiliation_strings":["Donghua University,College of Information Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,College of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045048913","display_name":"Longting Xu","orcid":"https://orcid.org/0000-0002-2329-895X"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longting Xu","raw_affiliation_strings":["Donghua University,College of Information Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,College of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Fortemedia Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fortemedia Singapore,Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72116405,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9595999717712402,"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/electromyography","display_name":"Electromyography","score":0.683293342590332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6007797718048096},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5983903408050537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5260070562362671},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.14911428093910217},{"id":"https://openalex.org/keywords/physical-medicine-and-rehabilitation","display_name":"Physical medicine and rehabilitation","score":0.09212309122085571},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06189414858818054}],"concepts":[{"id":"https://openalex.org/C2777515770","wikidata":"https://www.wikidata.org/wiki/Q507369","display_name":"Electromyography","level":2,"score":0.683293342590332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007797718048096},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5983903408050537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5260070562362671},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.14911428093910217},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.09212309122085571},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06189414858818054},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889321","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W2141998673","https://openalex.org/W2322064186","https://openalex.org/W2419247625","https://openalex.org/W2516342150","https://openalex.org/W2537327199","https://openalex.org/W2755891984","https://openalex.org/W2788241093","https://openalex.org/W2963045393","https://openalex.org/W2963321191","https://openalex.org/W2998832642","https://openalex.org/W3011475824","https://openalex.org/W3016447038","https://openalex.org/W3016912202","https://openalex.org/W3095095816","https://openalex.org/W3095136073","https://openalex.org/W3100604685","https://openalex.org/W3105229878","https://openalex.org/W3210530853","https://openalex.org/W4221147453","https://openalex.org/W4372264243","https://openalex.org/W4385807442","https://openalex.org/W4395447416","https://openalex.org/W4405490053","https://openalex.org/W4406461266","https://openalex.org/W6636885848","https://openalex.org/W6688816777","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2376139493","https://openalex.org/W2911808920","https://openalex.org/W2141253262","https://openalex.org/W3156756500","https://openalex.org/W4251090744","https://openalex.org/W2386293158","https://openalex.org/W2433638048"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"aims":[3],"to":[4,26,130],"improve":[5],"the":[6,131],"clarity,":[7],"intelligibility,":[8],"and":[9,35,117,149],"quality":[10,116],"of":[11,142],"speech":[12,16,22,47,60,115],"signals":[13,96,99],"for":[14,66],"various":[15],"enabled":[17],"applications.":[18],"However,":[19],"air-conducted":[20],"(AC)":[21,133],"is":[23],"highly":[24],"susceptible":[25],"ambient":[27],"noise,":[28],"particularly":[29],"in":[30,45,48,68,114,123],"low":[31,125,146],"signal-to-noise":[32],"ratio":[33],"(SNR)":[34],"non-stationary":[36],"noise":[37],"environments.":[38],"Incorporating":[39],"multi-modal":[40],"information":[41],"has":[42],"shown":[43],"promise":[44],"enhancing":[46],"such":[49],"challenging":[50],"scenarios.":[51],"Electromyography":[52],"(EMG)":[53],"signals,":[54],"which":[55],"capture":[56],"muscle":[57],"activity":[58],"during":[59],"production,":[61],"offer":[62],"noise-resistant":[63],"properties":[64],"beneficial":[65],"SE":[67,74,132],"adverse":[69],"conditions.":[70],"Most":[71],"previous":[72],"EMG-based":[73],"methods":[75],"required":[76],"35":[77],"EMG":[78,95],"channels,":[79],"limiting":[80],"their":[81],"practicality.":[82],"To":[83],"address":[84],"this,":[85],"we":[86],"propose":[87],"a":[88,101,138],"novel":[89],"method":[90,136],"that":[91],"considers":[92],"only":[93],"8-channel":[94],"with":[97,105],"acoustic":[98],"using":[100],"modified":[102],"SEMamba":[103],"network":[104],"added":[106],"cross-modality":[107],"modules.":[108],"Our":[109],"experiments":[110],"demonstrate":[111],"substantial":[112],"improvements":[113],"intelligibility":[118],"over":[119],"traditional":[120],"approaches,":[121],"especially":[122],"extremely":[124],"SNR":[126,147],"settings.":[127],"Notably,":[128],"compared":[129],"approach,":[134],"our":[135],"achieves":[137],"significant":[139],"PESQ":[140],"gain":[141],"0.235":[143],"under":[144,151],"matched":[145],"conditions":[148],"0.527":[150],"mismatched":[152],"conditions,":[153],"highlighting":[154],"its":[155],"robustness.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}