{"id":"https://openalex.org/W2998678989","doi":"https://doi.org/10.1109/waspaa.2019.8937186","title":"Attention Wave-U-Net for Speech Enhancement","display_name":"Attention Wave-U-Net for Speech Enhancement","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2998678989","doi":"https://doi.org/10.1109/waspaa.2019.8937186","mag":"2998678989"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ritwik Giri","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Umut Isik","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.4327,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.99426386,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"253"},"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":0.9998000264167786,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8005213737487793},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7000536322593689},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6999714970588684},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6911929249763489},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.671630859375},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5322211980819702},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5010926723480225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4367876648902893},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4271862208843231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37378475069999695},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08638793230056763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8005213737487793},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7000536322593689},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6999714970588684},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6911929249763489},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.671630859375},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5322211980819702},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5010926723480225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4367876648902893},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4271862208843231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37378475069999695},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08638793230056763},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2019.8937186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1901129140","https://openalex.org/W1902237438","https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W2153894152","https://openalex.org/W2221409856","https://openalex.org/W2603567530","https://openalex.org/W2609883120","https://openalex.org/W2774707525","https://openalex.org/W2798122215","https://openalex.org/W2802304149","https://openalex.org/W2888358068","https://openalex.org/W2902132730","https://openalex.org/W2943554574","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963452667","https://openalex.org/W2963881378","https://openalex.org/W2963941778","https://openalex.org/W2972443522","https://openalex.org/W4245919820","https://openalex.org/W4289242435","https://openalex.org/W4385245566","https://openalex.org/W6639824700","https://openalex.org/W6739901393","https://openalex.org/W6746914816","https://openalex.org/W6750469568","https://openalex.org/W6751512325","https://openalex.org/W6753100508","https://openalex.org/W6756251360"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W2131486661"],"abstract_inverted_index":{"We":[0,31,70,88],"propose":[1],"a":[2,15,82,103],"novel":[3],"application":[4],"of":[5,36,44,49,98],"an":[6,79],"attention":[7,19,38,76],"mechanism":[8,39],"in":[9,47],"neural":[10],"speech":[11,52,60,107],"enhancement,":[12],"by":[13],"presenting":[14],"U-Net":[16],"architecture":[17],"with":[18],"mechanism,":[20],"which":[21],"processes":[22],"the":[23,34,37,42,45,50,64,73,96,99],"raw":[24],"waveform":[25],"directly,":[26],"and":[27,55],"is":[28],"trained":[29],"end-to-end.":[30],"find":[32],"that":[33,72],"inclusion":[35],"significantly":[40],"improves":[41],"performance":[43],"model":[46],"terms":[48],"objective":[51],"quality":[53],"metrics,":[54],"outperforms":[56],"all":[57],"other":[58],"published":[59],"enhancement":[61],"approaches":[62],"on":[63],"Voice":[65,84],"Bank":[66],"Corpus":[67],"(VCTK)":[68],"dataset.":[69],"observe":[71],"final":[74],"layer":[75],"mask":[77],"has":[78],"interpretation":[80],"as":[81,102],"soft":[83],"Activity":[85],"Detector":[86],"(VAD).":[87],"also":[89],"present":[90],"some":[91],"initial":[92],"results":[93],"to":[94,106],"show":[95],"efficacy":[97],"proposed":[100],"system":[101],"pre-processing":[104],"step":[105],"recognition":[108],"systems.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}