{"id":"https://openalex.org/W4394724670","doi":"https://doi.org/10.1186/s13636-024-00341-x","title":"Supervised Attention Multi-Scale Temporal Convolutional Network for monaural speech enhancement","display_name":"Supervised Attention Multi-Scale Temporal Convolutional Network for monaural speech enhancement","publication_year":2024,"publication_date":"2024-04-11","ids":{"openalex":"https://openalex.org/W4394724670","doi":"https://doi.org/10.1186/s13636-024-00341-x"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00341-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00341-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00341-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00341-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090668921","display_name":"Zehua Zhang","orcid":"https://orcid.org/0000-0003-3215-5317"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"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, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388629","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0002-3469-2899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["NIO Automobile Co., LTD, Lane 56, Antuo Road, Anting Town, Jiading District, Shanghai, 201800, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIO Automobile Co., LTD, Lane 56, Antuo Road, Anting Town, Jiading District, Shanghai, 201800, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044255594","display_name":"Xuyi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"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":"Xuyi Zhuang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073118994","display_name":"Yukun Qian","orcid":"https://orcid.org/0000-0001-9095-4024"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"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":"Yukun Qian","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"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":true,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, No. 6, Pingshan 1st Road, Taoyuan Street, Shenzhen, 518000, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009651653"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.9416,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94413686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"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":0.9940999746322632,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9933000206947327,"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/monaural","display_name":"Monaural","score":0.8249956965446472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5699484944343567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5000264644622803},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4772474765777588},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4183056354522705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39683011174201965},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06592181324958801},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.055216968059539795}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8249956965446472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5699484944343567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5000264644622803},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4772474765777588},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4183056354522705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39683011174201965},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06592181324958801},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.055216968059539795},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00341-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00341-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00341-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:af44796838524fccbd1cdaf6fd32c362","is_oa":true,"landing_page_url":"https://doaj.org/article/af44796838524fccbd1cdaf6fd32c362","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-16 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00341-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00341-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00341-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1265899161","display_name":null,"funder_award_id":"62176102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1828714495","display_name":null,"funder_award_id":"2020B1515120004","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G3929901318","display_name":null,"funder_award_id":"62276076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4949529322","display_name":null,"funder_award_id":"No.62276076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7765127861","display_name":null,"funder_award_id":"No.2020B1515120004","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G8596076358","display_name":null,"funder_award_id":"No.62176102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394724670.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1963970749","https://openalex.org/W2027804983","https://openalex.org/W2070126272","https://openalex.org/W2086139506","https://openalex.org/W2108819501","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2155998647","https://openalex.org/W2158336491","https://openalex.org/W2169147844","https://openalex.org/W2236262108","https://openalex.org/W2291877678","https://openalex.org/W2395519940","https://openalex.org/W2558580397","https://openalex.org/W2889442120","https://openalex.org/W2952218014","https://openalex.org/W2952979007","https://openalex.org/W2963045393","https://openalex.org/W2963189033","https://openalex.org/W2991361823","https://openalex.org/W2998445964","https://openalex.org/W3015199127","https://openalex.org/W3015654783","https://openalex.org/W3017350693","https://openalex.org/W3019433526","https://openalex.org/W3025800305","https://openalex.org/W3095820034","https://openalex.org/W3096408984","https://openalex.org/W3097817799","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3147539069","https://openalex.org/W3170697543","https://openalex.org/W3174609245","https://openalex.org/W3197042120","https://openalex.org/W3197627016","https://openalex.org/W3211408542","https://openalex.org/W3213188934","https://openalex.org/W3215881519","https://openalex.org/W4385822821","https://openalex.org/W6603242443","https://openalex.org/W6679338098"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W2401567014","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"Abstract":[0],"Speech":[1],"signals":[2],"are":[3],"often":[4],"distorted":[5],"by":[6],"reverberation":[7],"and":[8,39,58,89,139,153],"noise,":[9],"with":[10,123],"a":[11,41,66,102,124],"widely":[12],"distributed":[13],"signal-to-noise":[14],"ratio":[15,92],"(SNR).":[16],"To":[17],"address":[18],"this,":[19],"our":[20],"study":[21],"develops":[22],"robust,":[23],"deep":[24],"neural":[25],"network":[26,134],"(DNN)-based":[27],"speech":[28,36,68,143,151],"enhancement":[29,37,69],"methods.":[30],"We":[31],"reproduce":[32],"several":[33],"DNN-based":[34],"monaural":[35],"methods":[38,158],"outline":[40],"strategy":[42],"for":[43,86,95],"constructing":[44],"datasets.":[45],"This":[46],"strategy,":[47],"validated":[48],"through":[49],"experimental":[50],"reproductions,":[51],"has":[52],"effectively":[53,118],"enhanced":[54],"the":[55,61,81,114,136,142],"denoising":[56,163],"efficiency":[57],"robustness":[59],"of":[60],"models.":[62],"Then,":[63],"we":[64],"propose":[65],"causal":[67],"system":[70],"named":[71],"Supervised":[72],"Attention":[73],"Multi-Scale":[74],"Temporal":[75],"Convolutional":[76],"Network":[77],"(SA-MSTCN).":[78],"SA-MSTCN":[79,146],"extracts":[80],"complex":[82,91],"compressed":[83],"spectrum":[84],"(CCS)":[85],"input":[87],"encoding":[88],"employs":[90],"masking":[93],"(CRM)":[94],"output":[96],"decoding.":[97],"The":[98,130],"supervised":[99,115],"attention":[100,116],"module,":[101],"lightweight":[103],"addition":[104],"to":[105,156],"SA-MSTCN,":[106],"guides":[107],"feature":[108],"extraction.":[109],"Experiment":[110],"results":[111],"show":[112],"that":[113],"module":[117],"improves":[119],"noise":[120],"reduction":[121],"performance":[122,164],"minor":[125],"increase":[126],"in":[127],"computational":[128],"cost.":[129],"multi-scale":[131],"temporal":[132],"convolutional":[133],"refines":[135],"perceptual":[137],"field":[138],"better":[140],"reconstructs":[141],"signal.":[144],"Overall,":[145],"not":[147],"only":[148],"achieves":[149],"state-of-the-art":[150],"quality":[152],"intelligibility":[154],"compared":[155],"other":[157],"but":[159],"also":[160],"maintains":[161],"stable":[162],"across":[165],"various":[166],"environments.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}