{"id":"https://openalex.org/W3162420637","doi":"https://doi.org/10.1109/icassp39728.2021.9414721","title":"Cascaded Time + Time-Frequency Unet For Speech Enhancement: Jointly Addressing Clipping, Codec Distortions, And Gaps","display_name":"Cascaded Time + Time-Frequency Unet For Speech Enhancement: Jointly Addressing Clipping, Codec Distortions, And Gaps","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162420637","doi":"https://doi.org/10.1109/icassp39728.2021.9414721","mag":"3162420637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5037296813","display_name":"Arun Asokan Nair","orcid":"https://orcid.org/0000-0002-6857-4313"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Asokan Nair","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7153","last_page":"7157"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8020281791687012},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.794619083404541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6906448602676392},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5848235487937927},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5803699493408203},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.5609245300292969},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5384606719017029},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.529728353023529},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4959190785884857},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4803665578365326},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47567954659461975},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4495936930179596},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.44771379232406616},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42531245946884155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4243304431438446},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4152213931083679},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.4147886633872986},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.4112277030944824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3448460102081299},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23403528332710266},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10441771149635315},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06796842813491821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020281791687012},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.794619083404541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6906448602676392},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5848235487937927},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5803699493408203},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.5609245300292969},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5384606719017029},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.529728353023529},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4959190785884857},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4803665578365326},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47567954659461975},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4495936930179596},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.44771379232406616},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42531245946884155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4243304431438446},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4152213931083679},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.4147886633872986},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.4112277030944824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3448460102081299},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23403528332710266},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10441771149635315},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06796842813491821},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W181032131","https://openalex.org/W1495679096","https://openalex.org/W1510355813","https://openalex.org/W1522301498","https://openalex.org/W1586645951","https://openalex.org/W1901129140","https://openalex.org/W2070126272","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2191779130","https://openalex.org/W2322799359","https://openalex.org/W2394461504","https://openalex.org/W2711335087","https://openalex.org/W2809824582","https://openalex.org/W2929274168","https://openalex.org/W2944209089","https://openalex.org/W2952218014","https://openalex.org/W2962946126","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W2981560594","https://openalex.org/W2997007695","https://openalex.org/W3011573174","https://openalex.org/W3015278429","https://openalex.org/W3015780049","https://openalex.org/W3025293551","https://openalex.org/W3043119899","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6751512325","https://openalex.org/W6769194633","https://openalex.org/W6777814698"],"related_works":["https://openalex.org/W4394596895","https://openalex.org/W137020845","https://openalex.org/W2124860381","https://openalex.org/W2151333624","https://openalex.org/W2496295964","https://openalex.org/W1542588102","https://openalex.org/W2910493550","https://openalex.org/W2105759788","https://openalex.org/W2361358457","https://openalex.org/W2005139297"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,15],"aims":[2],"to":[3,26,86],"improve":[4],"speech":[5,14,27,35],"quality":[6],"by":[7],"eliminating":[8],"noise":[9],"and":[10,32,39,50],"distortions.":[11],"While":[12],"most":[13],"methods":[16],"address":[17,87],"signal":[18,30],"independent":[19],"additive":[20],"sources":[21],"of":[22,53,59,106],"noise,":[23],"several":[24],"degradations":[25],"signals":[28],"are":[29],"dependent":[31],"non-additive,":[33],"like":[34],"clipping,":[36],"codec":[37],"distortions,":[38],"gaps":[40],"in":[41],"speech.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,65],"first":[47],"systematically":[48],"study":[49],"achieve":[51],"state":[52],"the":[54,104],"art":[55],"results":[56],"on":[57],"each":[58,107],"these":[60],"three":[61,89],"distortions":[62,90],"individually.":[63],"Next,":[64],"demonstrate":[66],"a":[67,73,80,96],"neural":[68,77,84,108],"network":[69,78,85,109],"pipeline":[70],"that":[71,94],"cascades":[72],"time":[74],"domain":[75,82],"convolutional":[76,83],"with":[79],"time-frequency":[81],"all":[88],"jointly.":[91],"We":[92],"observe":[93],"such":[95],"cascade":[97],"achieves":[98],"good":[99],"performance":[100],"while":[101],"also":[102],"keeping":[103],"action":[105],"component":[110],"interpretable.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}