{"id":"https://openalex.org/W4394938960","doi":"https://doi.org/10.1109/taslp.2024.3389632","title":"A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement","display_name":"A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394938960","doi":"https://doi.org/10.1109/taslp.2024.3389632"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3389632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3389632","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5112168875","display_name":"Bengt Borgstr\u00f6m","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bengt J. Borgstr\u00f6m","raw_affiliation_strings":["MIT Lincoln Laboratory, Artificial Intelligence Technology and Systems Group, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Artificial Intelligence Technology and Systems Group, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086705866","display_name":"M.S. Brandstein","orcid":"https://orcid.org/0009-0008-7883-3658"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael S. Brandstein","raw_affiliation_strings":["MIT Lincoln Laboratory, Artificial Intelligence Technology and Systems Group, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Artificial Intelligence Technology and Systems Group, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112168875"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":1.8677,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85217112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"2418","last_page":"2431"},"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":0.9995999932289124,"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":0.9986000061035156,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.9132134914398193},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6792861223220825},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6002668142318726},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.576546847820282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4985616207122803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36000049114227295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2822501063346863},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07079565525054932}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.9132134914398193},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6792861223220825},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6002668142318726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.576546847820282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4985616207122803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36000049114227295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2822501063346863},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07079565525054932}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3389632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3389632","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4158783420","display_name":null,"funder_award_id":"FA8702-15-D-0001","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1557133539","https://openalex.org/W1635512741","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1922655562","https://openalex.org/W1972475755","https://openalex.org/W1974387177","https://openalex.org/W1975301756","https://openalex.org/W1989034586","https://openalex.org/W1992475611","https://openalex.org/W2016449517","https://openalex.org/W2031717928","https://openalex.org/W2067295501","https://openalex.org/W2076608692","https://openalex.org/W2094721231","https://openalex.org/W2121973264","https://openalex.org/W2128402994","https://openalex.org/W2136682440","https://openalex.org/W2142591210","https://openalex.org/W2144404214","https://openalex.org/W2153485077","https://openalex.org/W2162488555","https://openalex.org/W2168959749","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2490695385","https://openalex.org/W2510942155","https://openalex.org/W2514828952","https://openalex.org/W2549139847","https://openalex.org/W2752782242","https://openalex.org/W2800231483","https://openalex.org/W2801554275","https://openalex.org/W2802304149","https://openalex.org/W2889286744","https://openalex.org/W2889540509","https://openalex.org/W2891607145","https://openalex.org/W2898446161","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962998773","https://openalex.org/W2963040451","https://openalex.org/W2963045393","https://openalex.org/W2963323244","https://openalex.org/W2963443859","https://openalex.org/W2963446712","https://openalex.org/W2971417062","https://openalex.org/W2972443522","https://openalex.org/W2987989623","https://openalex.org/W2991361823","https://openalex.org/W2998678989","https://openalex.org/W3016109656","https://openalex.org/W3016213974","https://openalex.org/W3024869864","https://openalex.org/W3096831136","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3103902067","https://openalex.org/W3111051109","https://openalex.org/W3126648213","https://openalex.org/W3147539069","https://openalex.org/W3161950572","https://openalex.org/W3162493033","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3177048943","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W4221162870","https://openalex.org/W4283010431","https://openalex.org/W4289242435","https://openalex.org/W4302067267","https://openalex.org/W4312271884","https://openalex.org/W6631190155","https://openalex.org/W6640090968","https://openalex.org/W6688816777","https://openalex.org/W6756251360","https://openalex.org/W6790299203","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W4404782863","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Neural":[0],"network":[1,35,117],"approaches":[2],"to":[3,59,97,132,138,148],"single-channel":[4],"speech":[5,36,125,161,166],"enhancement":[6,154],"have":[7,16],"received":[8],"much":[9],"recent":[10,115],"attention.":[11],"In":[12],"particular,":[13],"mask-based":[14,32],"architectures":[15],"achieved":[17],"significant":[18],"performance":[19,135],"improvements":[20],"over":[21],"conventional":[22,139],"methods.":[23],"This":[24],"paper":[25],"proposes":[26],"a":[27,54,61,76,150],"multiscale":[28,64,116],"autoencoder":[29],"(MSAE)":[30],"for":[31],"end-to-end":[33,102],"neural":[34,103],"enhancement.":[37],"The":[38,66,109],"MSAE":[39,88,110,131],"performs":[40],"spectral":[41,78],"decomposition":[42],"of":[43,63,72,92,152,159],"an":[44,101],"input":[45],"waveform":[46],"within":[47,100],"separate":[48],"band-limited":[49],"branches,":[50],"each":[51],"operating":[52],"with":[53],"different":[55],"rate":[56],"and":[57,105,119,164],"scale,":[58],"extract":[60],"sequence":[62],"embeddings.":[65],"proposed":[67,144],"framework":[68,145],"features":[69],"intuitive":[70],"parameterization":[71],"the":[73,83,87,130,143],"autoencoder,":[74],"including":[75],"flexible":[77],"band":[79],"design":[80],"based":[81],"on":[82],"Constant-Q":[84],"transform.":[85],"Additionally,":[86,142],"is":[89,146],"constructed":[90],"entirely":[91],"differentiable":[93],"operators,":[94],"allowing":[95],"it":[96],"be":[98,106],"implemented":[99],"network,":[104],"discriminatively":[107],"trained.":[108],"draws":[111],"motivation":[112],"both":[113,156],"from":[114,120],"topologies":[118],"traditional":[121],"multiresolution":[122],"transforms":[123],"in":[124,157],"processing.":[126],"Experimental":[127],"results":[128],"show":[129],"provide":[133],"clear":[134],"benefits":[136],"relative":[137],"single-branch":[140],"autoencoders.":[141],"shown":[147],"outperform":[149],"variety":[151],"state-of-the-art":[153],"systems,":[155],"terms":[158],"objective":[160],"quality":[162],"metrics":[163],"automatic":[165],"recognition":[167],"accuracy.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}