{"id":"https://openalex.org/W3015352480","doi":"https://doi.org/10.1109/icassp40776.2020.9054499","title":"A Dual-Staged Context Aggregation Method towards Efficient End-to-End Speech Enhancement","display_name":"A Dual-Staged Context Aggregation Method towards Efficient End-to-End Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015352480","doi":"https://doi.org/10.1109/icassp40776.2020.9054499","mag":"3015352480"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5047870570","display_name":"Kai Zhen","orcid":"https://orcid.org/0000-0003-4133-8158"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhen","raw_affiliation_strings":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005473429","display_name":"Mi Suk Lee","orcid":"https://orcid.org/0000-0001-8951-5032"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mi Suk Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.493,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.56656113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"370"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8550131916999817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8050673604011536},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7687984704971313},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6751118898391724},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.580095112323761},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5768027305603027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5578330755233765},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5194758772850037},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5124209523200989},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46325454115867615},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4601185619831085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43411242961883545},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42186278104782104},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14646968245506287},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09145531058311462}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8550131916999817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050673604011536},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7687984704971313},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6751118898391724},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.580095112323761},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5768027305603027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5578330755233765},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5194758772850037},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5124209523200989},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46325454115867615},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4601185619831085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43411242961883545},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42186278104782104},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14646968245506287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09145531058311462},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W185399533","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1924770834","https://openalex.org/W1974387177","https://openalex.org/W2044893557","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2194775991","https://openalex.org/W2291877678","https://openalex.org/W2519091744","https://openalex.org/W2678916739","https://openalex.org/W2889442120","https://openalex.org/W2891355459","https://openalex.org/W2938874599","https://openalex.org/W2939378741","https://openalex.org/W2949382160","https://openalex.org/W2950237361","https://openalex.org/W2952218014","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2963446712","https://openalex.org/W2963452667","https://openalex.org/W2963751183","https://openalex.org/W2963840672","https://openalex.org/W2964121744","https://openalex.org/W2972354707","https://openalex.org/W2972542211","https://openalex.org/W3099330747","https://openalex.org/W6607486085","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6696085341","https://openalex.org/W6751512325"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4312751558"],"abstract_inverted_index":{"In":[0,46],"speech":[1,11,16],"enhancement,":[2],"an":[3,39,83],"end-to-end":[4],"deep":[5],"neural":[6],"network":[7,57],"converts":[8],"a":[9,14,33,51,59],"noisy":[10],"signal":[12,37],"to":[13,62,129],"clean":[15],"directly":[17],"in":[18],"the":[19,69,112],"time":[20,35],"domain":[21,36],"without":[22],"time-frequency":[23],"transformation":[24],"or":[25],"mask":[26],"estimation.":[27],"However,":[28],"aggregating":[29],"contextual":[30],"information":[31],"from":[32],"high-resolution":[34],"with":[38,82,103,131],"affordable":[40],"model":[41],"complexity":[42],"still":[43,117],"remains":[44],"challenging.":[45],"this":[47],"paper,":[48],"we":[49],"propose":[50],"densely":[52],"connected":[53],"convolutional":[54,80],"and":[55,72,89],"recurrent":[56],"(DCCRN),":[58],"hybrid":[60],"architecture,":[61],"enable":[63],"dual-staged":[64],"temporal":[65],"context":[66],"aggregation.":[67],"With":[68],"dense":[70],"connectivity":[71],"cross-component":[73],"identical":[74],"shortcut,":[75],"DCCRN":[76],"consistently":[77],"outperforms":[78],"competing":[79],"baselines":[81],"average":[84],"STOI":[85],"improvement":[86],"of":[87,91],"0.23":[88],"PESQ":[90],"1.38":[92,105],"at":[93],"three":[94],"SNR":[95],"levels.":[96],"The":[97,108],"proposed":[98],"method":[99],"is":[100,116,125],"computationally":[101],"efficient":[102],"only":[104],"million":[106],"parameters.":[107,135],"generalizability":[109],"performance":[110],"on":[111],"unseen":[113],"noise":[114],"types":[115],"decent":[118],"considering":[119],"its":[120],"low":[121],"complexity,":[122],"although":[123],"it":[124],"relatively":[126],"weaker":[127],"comparing":[128],"Wave-U-Net":[130],"7.25":[132],"times":[133],"more":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}