{"id":"https://openalex.org/W4392904015","doi":"https://doi.org/10.1109/icassp48485.2024.10446787","title":"Lightweight Multi-Axial Transformer with Frequency Prompt for Single Channel Speech Enhancement","display_name":"Lightweight Multi-Axial Transformer with Frequency Prompt for Single Channel Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904015","doi":"https://doi.org/10.1109/icassp48485.2024.10446787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008366157","display_name":"Xingwei Liang","orcid":"https://orcid.org/0000-0002-5940-3440"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Liang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090668921","display_name":"Zehua Zhang","orcid":"https://orcid.org/0000-0003-3215-5317"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026719663","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0002-4009-5679"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210102458","display_name":"Novel (United States)","ror":"https://ror.org/00z5k4y41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102458"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ruifeng Xu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Peng Cheng Laboratory, Shenzhen, China","Harbin Institute of Technology (Shenzhen), Shenzhen, China","Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","institution_ids":["https://openalex.org/I4210102458"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10511","last_page":"10515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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/transformer","display_name":"Transformer","score":0.6723436713218689},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6572290658950806},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5055074691772461},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44819724559783936},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3453734517097473},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24822229146957397},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.23575642704963684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21269431710243225},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19091898202896118},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08655759692192078}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6723436713218689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572290658950806},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5055074691772461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44819724559783936},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3453734517097473},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24822229146957397},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.23575642704963684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21269431710243225},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19091898202896118},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08655759692192078},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2113131123","https://openalex.org/W2121973264","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2531409750","https://openalex.org/W2950116990","https://openalex.org/W2952218014","https://openalex.org/W2998161426","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3109394096","https://openalex.org/W3147539069","https://openalex.org/W3161950572","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3206809722","https://openalex.org/W3213188934","https://openalex.org/W4221149546","https://openalex.org/W4221162870","https://openalex.org/W4225672218","https://openalex.org/W4372260144","https://openalex.org/W4372267368","https://openalex.org/W4375869466","https://openalex.org/W6757632829","https://openalex.org/W6786372312"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3118578380","https://openalex.org/W4294326507","https://openalex.org/W2144085034","https://openalex.org/W2166153901","https://openalex.org/W2100095452","https://openalex.org/W182167794","https://openalex.org/W2151415191"],"abstract_inverted_index":{"Time-frequency":[0],"analysis":[1],"in":[2,100],"single-channel":[3],"speech":[4,27,101],"enhancement":[5],"has":[6,116],"received":[7],"considerable":[8],"attention.":[9],"While":[10],"Transformer-based":[11],"architectures":[12],"are":[13],"gaining":[14],"traction,":[15],"their":[16],"computational":[17,43,71],"burden":[18],"can":[19],"be":[20],"substantial,":[21],"especially":[22],"when":[23],"dealing":[24],"with":[25,119],"longer":[26],"samples.":[28],"To":[29],"address":[30],"this,":[31],"our":[32,57,114],"research":[33],"introduces":[34],"the":[35,60,76,87,95,128],"lightweight":[36],"multi-axial":[37],"Transformer":[38],"(LMA-Transformer)":[39],"optimized":[40],"for":[41],"low":[42],"overhead":[44],"while":[45],"efficiently":[46],"extracting":[47],"features":[48,82,99],"along":[49],"both":[50],"temporal":[51],"and":[52,124],"frequency":[53,88,98],"axes.":[54],"Major":[55],"to":[56,79,92,111],"approach":[58],"is":[59],"Temporal/Frequency":[61],"MultiDConv":[62],"head":[63],"self-attention":[64],"module":[65],"(T/F-MDHSA),":[66],"which":[67],"not":[68],"only":[69],"reduces":[70],"costs":[72],"but":[73],"also":[74],"improves":[75],"Transformer\u2019s":[77],"capability":[78],"utilize":[80],"local":[81],"effectively.":[83],"Moreover,":[84],"we":[85],"introduce":[86],"prompt":[89],"block,":[90],"designed":[91],"dynamically":[93],"guide":[94],"recovery":[96],"of":[97,108],"signals":[102],"that":[103],"have":[104],"experienced":[105],"varying":[106],"levels":[107],"degradation.":[109],"Compared":[110],"state-of-the-art":[112],"models,":[113],"model":[115],"competitive":[117],"performance":[118],"3.40":[120],"PESQ,":[121],"95.8%":[122],"STOI,":[123],"10.15":[125],"SSNR":[126],"on":[127],"VoiceBank":[129],"+":[130],"Demand":[131],"dataset.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}