{"id":"https://openalex.org/W2768009545","doi":"https://doi.org/10.1109/icdsp.2017.8096126","title":"A deep convolutional encoder-decoder model for robust speech dereverberation","display_name":"A deep convolutional encoder-decoder model for robust speech dereverberation","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2768009545","doi":"https://doi.org/10.1109/icdsp.2017.8096126","mag":"2768009545"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2017.8096126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2017.8096126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 22nd International Conference on Digital Signal Processing (DSP)","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/A5100445449","display_name":"Dawei Wang","orcid":"https://orcid.org/0000-0002-8670-1961"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"D. S. Wang","raw_affiliation_strings":["ADSPLAB/lntelligent Lab, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB/lntelligent Lab, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102747882","display_name":"Y. X. Zou","orcid":"https://orcid.org/0009-0006-7335-7272"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Y. X. Zou","raw_affiliation_strings":["ADSPLAB/lntelligent Lab, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB/lntelligent Lab, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102379100","display_name":"Weimin Shi","orcid":"https://orcid.org/0009-0004-2344-1025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W. Shi","raw_affiliation_strings":["Hian Speech Science & Technology Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Hian Speech Science & Technology Co., Ltd, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100445449"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59062996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"25 1","issue":null,"first_page":"1","last_page":"5"},"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":0.9966999888420105,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9930999875068665,"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":0.830916166305542},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7372128367424011},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6372294425964355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6079332232475281},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5795096158981323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4911968410015106},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4570479691028595},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.42278948426246643},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4170714020729065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4137214124202728},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07201948761940002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830916166305542},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7372128367424011},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6372294425964355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6079332232475281},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5795096158981323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4911968410015106},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4570479691028595},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.42278948426246643},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4170714020729065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4137214124202728},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07201948761940002},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/icdsp.2017.8096126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2017.8096126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 22nd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W61762298","https://openalex.org/W190060899","https://openalex.org/W1552314771","https://openalex.org/W1555217905","https://openalex.org/W1910657905","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2102072896","https://openalex.org/W2107363208","https://openalex.org/W2108661465","https://openalex.org/W2112739286","https://openalex.org/W2123138249","https://openalex.org/W2130640611","https://openalex.org/W2141998673","https://openalex.org/W2163605009","https://openalex.org/W2188162373","https://openalex.org/W2284628133","https://openalex.org/W2330127310","https://openalex.org/W2516342150","https://openalex.org/W2542605056","https://openalex.org/W2911394281","https://openalex.org/W2919115771","https://openalex.org/W2963453742","https://openalex.org/W2963881378"],"related_works":["https://openalex.org/W2017779656","https://openalex.org/W2001172292","https://openalex.org/W2169567031","https://openalex.org/W1849802015","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Research":[0],"shows":[1],"that":[2,41],"speech":[3,32],"dereverberation":[4],"(SD)":[5],"with":[6,66,101,124,147,166],"Deep":[7,88],"Neural":[8,50],"Network":[9,51],"(DNN)":[10],"achieves":[11],"the":[12,22,25,48,76,96,102,107,110,130,138,152,161,172,184,191],"state-of-the-art":[13],"results":[14],"by":[15,58],"learning":[16],"spectral":[17,28],"mapping,":[18],"which,":[19],"simultaneously,":[20],"lacks":[21],"characterization":[23],"of":[24,31,109,163,186],"local":[26,60],"temporal":[27],"structures":[29],"(LTSS)":[30],"signal":[33],"and":[34,62,132,174],"calls":[35],"for":[36,78,95],"a":[37,54,87,144],"large":[38],"storage":[39,126],"space":[40],"is":[42,93,141,156],"impractical":[43],"in":[44,99,114,143],"real":[45],"applications.":[46],"Contrarily,":[47],"Convolutional":[49,89],"(CNN)":[52],"offers":[53],"better":[55,167],"modeling":[56,118],"ability":[57],"considering":[59],"patterns":[61],"has":[63],"less":[64,148],"parameters":[65],"its":[67,115],"weights":[68],"sharing":[69],"property,":[70],"which":[71],"motivates":[72],"us":[73],"to":[74,84,182],"employ":[75],"CNN":[77],"SD":[79,103,188,193],"task.":[80],"In":[81],"this":[82],"paper,":[83],"our":[85],"knowledge,":[86],"Encoder-Decoder":[90],"(DCED)":[91],"model":[92,112,154,165],"proposed":[94,139],"first":[97],"time":[98],"dealing":[100],"task":[104],"(DCED-SD),":[105],"where":[106],"advantage":[108],"DCED-SD":[111,140,153],"lies":[113],"powerful":[116],"LTSS":[117],"capability":[119],"via":[120],"convolutional":[121],"encoder-decoder":[122],"layers":[123],"smaller":[125,159],"requirement.":[127],"By":[128,170],"taking":[129],"reverberant":[131,198],"anechoic":[133],"spectrum":[134],"as":[135],"training":[136],"pairs,":[137],"well-trained":[142],"supervised":[145],"manner":[146],"convergence":[149],"time.":[150],"Additionally,":[151],"size":[155,162],"23":[157],"times":[158],"than":[160],"DNN-SD":[164],"performance":[168],"achieved.":[169],"using":[171],"simulated":[173],"real-recorded":[175],"data,":[176],"extensive":[177],"experiments":[178],"have":[179],"been":[180],"conducted":[181],"demonstrate":[183],"superiority":[185],"DCED-based":[187],"method":[189,194],"over":[190],"DNN-based":[192],"under":[195],"different":[196],"unseen":[197],"conditions.":[199]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}