{"id":"https://openalex.org/W4409672222","doi":"https://doi.org/10.1587/transinf.2024edl8099","title":"Monaural Speech Enhancement Based on Multi-Resolution Feature Analysis","display_name":"Monaural Speech Enhancement Based on Multi-Resolution Feature Analysis","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409672222","doi":"https://doi.org/10.1587/transinf.2024edl8099"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edl8099","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8099","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8099/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8099/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuewei ZHANG","orcid":null},"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":["Department of Electronic Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031888988","display_name":"Huanbin Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huanbin ZOU","raw_affiliation_strings":["Xiaohongshu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc","institution_ids":[]}]},{"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":["Department of Electronic Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9556,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8488031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"E108.D","issue":"11","first_page":"1421","last_page":"1426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.984499990940094,"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":0.984499990940094,"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/monaural","display_name":"Monaural","score":0.9265173673629761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8810036182403564},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.644632875919342},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5550602674484253},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5512635111808777},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5269946455955505},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5061714053153992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4860113561153412},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08527633547782898}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9265173673629761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8810036182403564},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.644632875919342},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5550602674484253},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5512635111808777},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5269946455955505},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5061714053153992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860113561153412},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08527633547782898},{"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:10.1587/transinf.2024edl8099","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8099","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8099/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edl8099","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8099","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8099/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4409672222.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2031614119","https://openalex.org/W2094721231","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2889442120","https://openalex.org/W2991361823","https://openalex.org/W3016361963","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3162493033","https://openalex.org/W3198680319","https://openalex.org/W3213188934","https://openalex.org/W4221149546","https://openalex.org/W4232282348","https://openalex.org/W4297841575","https://openalex.org/W4372259751","https://openalex.org/W4372267368","https://openalex.org/W4387026472","https://openalex.org/W4392903057","https://openalex.org/W4392904390","https://openalex.org/W4392909610"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W2401567014","https://openalex.org/W2538939196","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Multi-resolution":[0],"spectrum":[1,47,64,74],"feature":[2],"analysis":[3],"has":[4],"demonstrated":[5],"superior":[6],"performance":[7,133],"over":[8],"traditional":[9],"single-resolution":[10],"methods":[11,18],"in":[12],"speech":[13],"enhancement.":[14],"However,":[15],"previous":[16],"multi-resolution-based":[17],"typically":[19],"have":[20],"limited":[21],"use":[22],"of":[23],"multi-resolution":[24,46,63,72,90,118,127],"features,":[25],"and":[26,59,70,88,134],"some":[27],"suffer":[28],"from":[29],"high":[30],"model":[31,85],"complexity.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,95,115],"propose":[37],"a":[38,54,61,117],"more":[39,92],"lightweight":[40],"method":[41],"that":[42,124],"fully":[43],"leverages":[44],"the":[45,79,84,97,107,125],"features.":[48],"Our":[49],"approach":[50],"is":[51],"based":[52],"on":[53],"convolutional":[55],"recurrent":[56],"network":[57],"(CRN)":[58],"employs":[60],"low-complexity":[62],"fusion":[65],"(MRSF)":[66],"block":[67],"to":[68,86],"handle":[69],"fuse":[71],"noisy":[73],"information.":[75],"We":[76],"also":[77],"improve":[78],"existing":[80],"encoder-decoder":[81],"structure,":[82],"enabling":[83],"extract":[87],"analyze":[89],"features":[91],"effectively.":[93],"Furthermore,":[94],"adopt":[96],"short-time":[98],"discrete":[99],"cosine":[100],"transform":[101],"(STDCT)":[102],"for":[103],"time-frequency":[104],"transformation,":[105],"avoiding":[106],"phase":[108],"estimation":[109],"problem.":[110],"To":[111],"optimize":[112],"our":[113],"model,":[114],"design":[116],"STDCT":[119],"loss":[120],"function.":[121],"Experiments":[122],"demonstrate":[123],"proposed":[126],"STDCT-based":[128],"CRN":[129],"(MRCRN)":[130],"achieves":[131],"excellent":[132],"outperforms":[135],"current":[136],"advanced":[137],"systems.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}