{"id":"https://openalex.org/W4392903057","doi":"https://doi.org/10.1109/icassp48485.2024.10447096","title":"A Two-Stage Framework in Cross-Spectrum Domain for Real-Time Speech Enhancement","display_name":"A Two-Stage Framework in Cross-Spectrum Domain for Real-Time Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903057","doi":"https://doi.org/10.1109/icassp48485.2024.10447096"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447096","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/A5004726078","display_name":"Yuewei Zhang","orcid":"https://orcid.org/0000-0002-9124-0194"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewei Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031888988","display_name":"Huanbin Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanbin Zou","raw_affiliation_strings":["Tencent Video Cloud,Shanghai,China","Tencent Video Cloud, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Video Cloud,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Video Cloud, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446909","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0003-2133-4651"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0058,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9599264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12587","last_page":"12591"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9976000189781189,"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/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.7655103206634521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7368529438972473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6173046827316284},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5915852189064026},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5606541633605957},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5375065803527832},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5006308555603027},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4860156178474426},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4723052978515625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4616820216178894},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.4504269063472748},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.44657790660858154},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.43243199586868286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4304327964782715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3540222942829132},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18150746822357178},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1188870370388031},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10988333821296692},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08499610424041748},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08434054255485535}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.7655103206634521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368529438972473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6173046827316284},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5915852189064026},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5606541633605957},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5375065803527832},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5006308555603027},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4860156178474426},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4723052978515625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4616820216178894},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.4504269063472748},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.44657790660858154},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.43243199586868286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4304327964782715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3540222942829132},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18150746822357178},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1188870370388031},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10988333821296692},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08499610424041748},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08434054255485535},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447096","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":[{"id":"https://openalex.org/G4209639005","display_name":null,"funder_award_id":"CJGJZD20220517141400002","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"}],"funders":[{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2031614119","https://openalex.org/W2070126272","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2889442120","https://openalex.org/W2963868408","https://openalex.org/W2998161426","https://openalex.org/W3015199127","https://openalex.org/W3015424358","https://openalex.org/W3017350693","https://openalex.org/W3095248373","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3126648213","https://openalex.org/W3162493033","https://openalex.org/W3197260772","https://openalex.org/W3213188934","https://openalex.org/W4296068619","https://openalex.org/W6757632829","https://openalex.org/W6790299203"],"related_works":["https://openalex.org/W2402466562","https://openalex.org/W2782295999","https://openalex.org/W2162306796","https://openalex.org/W1970292246","https://openalex.org/W2016162169","https://openalex.org/W4247952185","https://openalex.org/W1895367623","https://openalex.org/W1642462315","https://openalex.org/W2015118744","https://openalex.org/W2005619368"],"abstract_inverted_index":{"Two-stage":[0],"pipeline":[1],"is":[2,53,83,110],"popular":[3],"in":[4,25,45,55,72,115,136],"speech":[5,43,134],"enhancement":[6,135],"tasks":[7],"due":[8],"to":[9,35,157],"its":[10],"superiority":[11],"over":[12],"traditional":[13],"single-stage":[14],"methods.":[15,118],"The":[16,49,81],"current":[17],"two-stage":[18,124,149],"approaches":[19],"usually":[20],"enhance":[21],"the":[22,26,32,37,42,46,56,68,73,97,116,127,143,147],"magnitude":[23],"spectrum":[24,34,61,79,129],"first":[27],"stage,":[28],"and":[29,40,104,112,151],"further":[30],"modify":[31],"complex":[33],"suppress":[36],"residual":[38],"noise":[39,91],"recover":[41],"phase":[44,99,107],"second":[47,70],"stage.":[48],"above":[50,69],"whole":[51],"process":[52],"performed":[54],"short-time":[57,74],"Fourier":[58],"transform":[59,77],"(STFT)":[60],"domain.":[62,80,138],"In":[63],"this":[64],"paper,":[65],"we":[66,85,120],"re-implement":[67],"sub-process":[71],"discrete":[75],"cosine":[76],"(STDCT)":[78],"reason":[82],"that":[84,142],"have":[86],"found":[87],"STDCT":[88,101],"performs":[89],"greater":[90],"suppression":[92],"capability":[93],"than":[94],"STFT.":[95],"Additionally,":[96],"implicit":[98],"of":[100],"ensures":[102],"simpler":[103],"more":[105],"efficient":[106],"recovery,":[108],"which":[109],"challenging":[111],"computationally":[113],"expensive":[114],"STFT-based":[117],"Therefore,":[119],"propose":[121],"a":[122],"novel":[123],"framework":[125],"called":[126],"STFT-STDCT":[128],"fusion":[130],"network":[131],"(FDFNet)":[132],"for":[133],"cross-spectrum":[137],"Experimental":[139],"results":[140],"demonstrate":[141],"proposed":[144],"FDFNet":[145],"outperforms":[146],"previous":[148],"methods":[150],"also":[152],"exhibits":[153],"superior":[154],"performance":[155],"compared":[156],"other":[158],"advanced":[159],"systems.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
