{"id":"https://openalex.org/W3111051109","doi":"https://doi.org/10.1109/taslp.2020.3043655","title":"The Speech Enhancement via Attention Masking Network (SEAMNET): An End-to-end System for Joint Suppression of Noise and Reverberation","display_name":"The Speech Enhancement via Attention Masking Network (SEAMNET): An End-to-end System for Joint Suppression of Noise and Reverberation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3111051109","doi":"https://doi.org/10.1109/taslp.2020.3043655","mag":"3111051109"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3043655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3043655","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/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"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. Borgstrom","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexington, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexington, Massachusetts, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael S. Brandstein","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexington, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexington, Massachusetts, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112168875"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.1822,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.9279131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9972000122070312,"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/speech-enhancement","display_name":"Speech enhancement","score":0.6360542178153992},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6138088703155518},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5070805549621582},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47202032804489136},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.46596530079841614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4566776156425476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4191345274448395},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.27403026819229126},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20431369543075562},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1783362627029419},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13178196549415588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07950073480606079}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6360542178153992},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6138088703155518},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5070805549621582},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47202032804489136},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.46596530079841614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4566776156425476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4191345274448395},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.27403026819229126},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20431369543075562},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1783362627029419},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13178196549415588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07950073480606079},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3043655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3043655","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":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W20030414","https://openalex.org/W46219734","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1975301756","https://openalex.org/W1989034586","https://openalex.org/W1992475611","https://openalex.org/W2006129368","https://openalex.org/W2016449517","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2048142341","https://openalex.org/W2066561607","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2076063813","https://openalex.org/W2078528584","https://openalex.org/W2091270830","https://openalex.org/W2101042021","https://openalex.org/W2107992675","https://openalex.org/W2109215269","https://openalex.org/W2112099742","https://openalex.org/W2113509581","https://openalex.org/W2117658657","https://openalex.org/W2121973264","https://openalex.org/W2128402994","https://openalex.org/W2131132575","https://openalex.org/W2140828385","https://openalex.org/W2142591210","https://openalex.org/W2143612262","https://openalex.org/W2146324387","https://openalex.org/W2149072817","https://openalex.org/W2149441837","https://openalex.org/W2153384885","https://openalex.org/W2153485077","https://openalex.org/W2153894152","https://openalex.org/W2155889651","https://openalex.org/W2158336491","https://openalex.org/W2161784349","https://openalex.org/W2162488555","https://openalex.org/W2163605009","https://openalex.org/W2167071115","https://openalex.org/W2168959749","https://openalex.org/W2219249508","https://openalex.org/W2236262108","https://openalex.org/W2386778405","https://openalex.org/W2490695385","https://openalex.org/W2510942155","https://openalex.org/W2603567530","https://openalex.org/W2618530766","https://openalex.org/W2752782242","https://openalex.org/W2801554275","https://openalex.org/W2889286744","https://openalex.org/W2889540509","https://openalex.org/W2890964092","https://openalex.org/W2891607145","https://openalex.org/W2899638089","https://openalex.org/W2902132730","https://openalex.org/W2952218014","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2963420686","https://openalex.org/W2963443859","https://openalex.org/W2964121744","https://openalex.org/W2971417062","https://openalex.org/W2972443522","https://openalex.org/W2987989623","https://openalex.org/W2997901485","https://openalex.org/W2998678989","https://openalex.org/W3005262054","https://openalex.org/W3098606562","https://openalex.org/W3099330747","https://openalex.org/W3103902067","https://openalex.org/W3147539069","https://openalex.org/W4289242435","https://openalex.org/W4302156456","https://openalex.org/W6631190155","https://openalex.org/W6677267349","https://openalex.org/W6688816777","https://openalex.org/W6756251360"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3081694532","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"This":[0,67,100,129],"paper":[1,68,130,145,208],"proposes":[2,69,132,146],"the":[3,56,78,81,87,96,105,141,183],"Speech":[4],"Enhancement":[5],"via":[6,112],"Attention":[7],"Masking":[8],"Network":[9],"(SEAMNET),":[10],"a":[11,45,70,113,133,147,188],"neural":[12],"network-based":[13],"end-to-end":[14,30,126,171],"single-channel":[15],"speech":[16,98,127,199],"enhancement":[17,62,79,172,217],"system":[18,185],"designed":[19],"for":[20,150,154],"joint":[21,159],"suppression":[22,40,108,160],"of":[23,52,104,107,161,190,197,221],"noise":[24,39,163],"and":[25,63,80,164,202,213],"reverberation.":[26],"It":[27],"formalizes":[28],"an":[29,61,64,170],"network":[31,155,223],"architecture,":[32,143],"referred":[33],"to":[34,94,125,140,186],"as":[35],"b-Net,":[36],"which":[37,74,117,174],"accomplishes":[38],"through":[41],"attention":[42],"masking":[43,88],"in":[44,121,195],"learned":[46],"embedding":[47],"space.":[48],"A":[49],"key":[50],"contribution":[51],"SEAMNET":[53,93,111,184,212],"is":[54,118],"that":[55,85,158],"b-Net":[57,142],"architecture":[58],"contains":[59],"both":[60,77,194],"autoencoder":[65,82],"path.":[66],"novel":[71,148],"loss":[72],"function":[73],"simultaneously":[75],"trains":[76],"paths,":[83],"so":[84,157],"disabling":[86],"mechanism":[89],"during":[90],"inference":[91],"causes":[92],"reconstruct":[95],"input":[97],"signal.":[99],"allows":[101],"dynamic":[102],"control":[103],"level":[106],"applied":[109],"by":[110,169],"minimum":[114],"gain":[115],"level,":[116],"not":[119,176],"possible":[120],"other":[122],"state-of-the-art":[123,191],"approaches":[124],"enhancement.":[128],"also":[131],"perceptually-motivated":[134],"waveform":[135],"distance":[136],"measure.":[137],"In":[138],"addition":[139],"this":[144,207],"method":[149],"designing":[151],"target":[152],"waveforms":[153],"training,":[156],"additive":[162],"reverberation":[165],"can":[166],"be":[167],"performed":[168],"system,":[173],"has":[175],"been":[177],"previously":[178],"possible.":[179],"Experimental":[180],"results":[181],"show":[182],"outperform":[187],"variety":[189],"baselines":[192],"systems,":[193],"terms":[196],"objective":[198],"quality":[200],"measures":[201],"subjective":[203],"listening":[204],"tests.":[205],"Finally,":[206],"draws":[209],"parallels":[210],"between":[211],"conventional":[214],"statistical":[215],"model-based":[216],"approaches,":[218],"offering":[219],"interpretability":[220],"many":[222],"components.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}