{"id":"https://openalex.org/W4221162870","doi":"https://doi.org/10.1109/icassp43922.2022.9746169","title":"Speech Denoising in the Waveform Domain With Self-Attention","display_name":"Speech Denoising in the Waveform Domain With Self-Attention","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221162870","doi":"https://doi.org/10.1109/icassp43922.2022.9746169"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746169","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5042062740","display_name":"Zhifeng Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140792","display_name":"Universidad Cat\u00f3lica Santo Domingo","ror":"https://ror.org/04ytq6y86","country_code":"DO","type":"education","lineage":["https://openalex.org/I4210140792"]}],"countries":["DO"],"is_corresponding":false,"raw_author_name":"Zhifeng Kong","raw_affiliation_strings":["UCSD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSD","institution_ids":["https://openalex.org/I4210140792"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Ping","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ping","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042872365","display_name":"Ambrish Dantrey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ambrish Dantrey","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.4727,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.98583569,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7867","last_page":"7871"},"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":0.9994999766349792,"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":0.9993000030517578,"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/spectrogram","display_name":"Spectrogram","score":0.8043798208236694},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.762620210647583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7197933197021484},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6610355377197266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6042596101760864},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.602602481842041},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5807698369026184},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49976181983947754},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4450070559978485},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43983781337738037},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43097132444381714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41145840287208557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3292904198169708},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32319173216819763},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14487558603286743},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.07417955994606018}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8043798208236694},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.762620210647583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197933197021484},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6610355377197266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6042596101760864},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.602602481842041},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5807698369026184},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49976181983947754},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4450070559978485},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43983781337738037},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43097132444381714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41145840287208557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3292904198169708},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32319173216819763},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14487558603286743},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.07417955994606018},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746169","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1516630152","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1968939597","https://openalex.org/W2044893557","https://openalex.org/W2105393299","https://openalex.org/W2128653836","https://openalex.org/W2133340843","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2166841940","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2519091744","https://openalex.org/W2757519008","https://openalex.org/W2802304149","https://openalex.org/W2937484199","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2950258612","https://openalex.org/W2952218014","https://openalex.org/W2952979007","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963975282","https://openalex.org/W2972404066","https://openalex.org/W2972443522","https://openalex.org/W2998832642","https://openalex.org/W3015338123","https://openalex.org/W3095057960","https://openalex.org/W3097034112","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3160085755","https://openalex.org/W3197912330","https://openalex.org/W3200379731","https://openalex.org/W4245919820","https://openalex.org/W4385245566","https://openalex.org/W6639824700","https://openalex.org/W6662018355","https://openalex.org/W6696676114","https://openalex.org/W6712317276","https://openalex.org/W6739901393","https://openalex.org/W6751512325","https://openalex.org/W6753100508","https://openalex.org/W6753855596","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2595172197","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2084856301","https://openalex.org/W3127543252"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"CleanUNet,":[5],"a":[6,46],"causal":[7],"speech":[8,68],"denoising":[9],"model":[10,17,42],"on":[11,20],"the":[12,61],"raw":[13],"waveform.":[14],"The":[15,41,57],"proposed":[16,58],"is":[18,35,43],"based":[19],"an":[21],"encoder-decoder":[22],"architecture":[23],"combined":[24],"with":[25],"several":[26],"self-attention":[27],"blocks":[28],"to":[29,37],"refine":[30],"its":[31],"bottleneck":[32],"representations,":[33],"which":[34],"crucial":[36],"obtain":[38],"good":[39],"results.":[40],"optimized":[44],"through":[45],"set":[47],"of":[48,66],"losses":[49],"defined":[50],"over":[51],"both":[52],"waveform":[53],"and":[54,73],"multi-resolution":[55],"spectrograms.":[56],"method":[59],"outperforms":[60],"state-of-the-art":[62],"models":[63],"in":[64],"terms":[65],"denoised":[67],"quality":[69],"from":[70],"various":[71],"objective":[72],"subjective":[74],"evaluation":[75],"metrics.":[76],"<sup":[77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[79]},"counts_by_year":[{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}