{"id":"https://openalex.org/W2996935789","doi":"https://doi.org/10.1109/icct46805.2019.8947298","title":"An End-to-End Speech Enhancement Framework Using Stacked Multi-scale Blocks","display_name":"An End-to-End Speech Enhancement Framework Using Stacked Multi-scale Blocks","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2996935789","doi":"https://doi.org/10.1109/icct46805.2019.8947298","mag":"2996935789"},"language":"en","primary_location":{"id":"doi:10.1109/icct46805.2019.8947298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct46805.2019.8947298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","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":"https://openalex.org/A5101523731","display_name":"Tian Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tian Lan","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103276902","display_name":"Sen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011118786","display_name":"Yilan Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilan Lyu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046508827","display_name":"Chuan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Peng","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077109703","display_name":"Qiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101523731"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15686756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"535","last_page":"539"},"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":0.9958000183105469,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8164898157119751},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7800372838973999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6757806539535522},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5441284775733948},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.541968047618866},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5408336520195007},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.47798341512680054},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.47330155968666077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46146801114082336},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.454306423664093},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4331004023551941},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4108677804470062},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4073011875152588},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.30720821022987366},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.29412132501602173},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07946240901947021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164898157119751},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7800372838973999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6757806539535522},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5441284775733948},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.541968047618866},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5408336520195007},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.47798341512680054},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.47330155968666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46146801114082336},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.454306423664093},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4331004023551941},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4108677804470062},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4073011875152588},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30720821022987366},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.29412132501602173},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07946240901947021},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icct46805.2019.8947298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct46805.2019.8947298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1974387177","https://openalex.org/W2052666245","https://openalex.org/W2067295501","https://openalex.org/W2157331557","https://openalex.org/W2416045997","https://openalex.org/W2735663686","https://openalex.org/W2746654391","https://openalex.org/W2755177320","https://openalex.org/W2766624546","https://openalex.org/W2889286744","https://openalex.org/W2889442120","https://openalex.org/W2891607145","https://openalex.org/W2891778567","https://openalex.org/W2894651928","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962928529","https://openalex.org/W2963045393","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963443859","https://openalex.org/W2963453742","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3127686677","https://openalex.org/W4249235654","https://openalex.org/W6639824700","https://openalex.org/W6754899465","https://openalex.org/W6761625566"],"related_works":["https://openalex.org/W2402466562","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2089240210"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,70,89],"is":[2,61,72,82],"the":[3,14,27,52,55,58,68,78,87,107,110,113,119,124,133,139],"task":[4],"of":[5,101,109,141],"removing":[6],"additive":[7],"noise":[8],"from":[9],"a":[10,45,64],"speech":[11,37,48,69,80,88,102,142],"signal,":[12],"and":[13,77,144],"deep":[15],"learning-based":[16],"methods":[17,135],"have":[18],"recently":[19],"seen":[20],"great":[21],"progress.":[22],"However,":[23],"it's":[24],"difficult":[25],"for":[26],"widely":[28],"adopted":[29],"short-time":[30],"Fourier":[31],"transform":[32],"(STFT)":[33],"to":[34,50,74,97],"reconstruct":[35],"target":[36],"accurately":[38],"with":[39],"noisy":[40],"phase.":[41],"This":[42],"work":[43],"proposes":[44],"novel":[46],"end-to-end":[47],"framework":[49],"solve":[51],"problem.":[53],"In":[54,86],"pre-processing":[56],"stage,":[57],"time-domain":[59],"signal":[60],"transformed":[62],"into":[63,118],"two-dimensional":[65],"feature":[66],"representation,":[67],"module":[71],"used":[73],"enhance":[75],"it,":[76],"enhanced":[79],"waveform":[81],"reconstructed":[83],"by":[84,122],"post-processing.":[85],"module,":[90],"we":[91],"propose":[92],"stacked":[93],"multi-scale":[94],"block":[95],"(SMB)":[96],"capture":[98],"more":[99],"information":[100],"feature.":[103],"To":[104],"further":[105],"improve":[106,138],"performance":[108,149],"proposed":[111,134],"model,":[112],"evaluation":[114],"metrics":[115],"are":[116],"integrated":[117],"loss":[120],"function":[121],"using":[123],"multi-objective":[125],"joint":[126],"optimization":[127],"training":[128],"strategy.":[129],"Experiments":[130],"show":[131],"that":[132],"can":[136],"significantly":[137],"ability":[140],"enhancement,":[143],"it":[145],"also":[146],"shows":[147],"good":[148],"at":[150],"low":[151],"SNRs.":[152]},"counts_by_year":[],"updated_date":"2026-01-28T23:14:49.684275","created_date":"2025-10-10T00:00:00"}