{"id":"https://openalex.org/W3163306112","doi":"https://doi.org/10.1109/icassp39728.2021.9414695","title":"Speech Enhancement Autoencoder with Hierarchical Latent Structure","display_name":"Speech Enhancement Autoencoder with Hierarchical Latent Structure","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163306112","doi":"https://doi.org/10.1109/icassp39728.2021.9414695","mag":"3163306112"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414695","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":"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/A5058203980","display_name":"Koen Oostermeijer","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Koen Oostermeijer","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058203980"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6094,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65645707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2013","issue":null,"first_page":"671","last_page":"675"},"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":0.9979000091552734,"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":0.9941999912261963,"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/autoencoder","display_name":"Autoencoder","score":0.8746247291564941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7202635407447815},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7005211710929871},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5055527687072754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4931125342845917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3942415118217468},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39256560802459717}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8746247291564941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202635407447815},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7005211710929871},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5055527687072754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4931125342845917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3942415118217468},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39256560802459717},{"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/icassp39728.2021.9414695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414695","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":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W2042407743","https://openalex.org/W2044893557","https://openalex.org/W2078528584","https://openalex.org/W2105393299","https://openalex.org/W2105768884","https://openalex.org/W2115055618","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2133340843","https://openalex.org/W2141998673","https://openalex.org/W2145760110","https://openalex.org/W2153894152","https://openalex.org/W2158291955","https://openalex.org/W2194775991","https://openalex.org/W2405774341","https://openalex.org/W2516001803","https://openalex.org/W2517760955","https://openalex.org/W2525513494","https://openalex.org/W2558539285","https://openalex.org/W2612445135","https://openalex.org/W2778338786","https://openalex.org/W2891433113","https://openalex.org/W2892110446","https://openalex.org/W2963163009","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963420686","https://openalex.org/W2963453742","https://openalex.org/W2968917279","https://openalex.org/W2987989623","https://openalex.org/W2994689640","https://openalex.org/W3041956526","https://openalex.org/W3099283299","https://openalex.org/W3103902067","https://openalex.org/W3132918556","https://openalex.org/W3147539069","https://openalex.org/W3209141406","https://openalex.org/W4297775537","https://openalex.org/W6639824700","https://openalex.org/W6713658392","https://openalex.org/W6727220019","https://openalex.org/W6728226663","https://openalex.org/W6737664043","https://openalex.org/W6743731764","https://openalex.org/W6767164110","https://openalex.org/W6780593937","https://openalex.org/W6784751978","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4294770367"],"abstract_inverted_index":{"A":[0],"new":[1],"hierarchical":[2],"convolutional":[3],"neural":[4],"network-based":[5],"autoencoder":[6,133],"architecture":[7],"called":[8],"SEHAE":[9,118],"(Speech":[10],"Enhancement":[11],"Hierarchical":[12],"AutoEncoder)":[13],"is":[14,21,86],"introduced,":[15],"in":[16,66],"which":[17,81],"the":[18,60,63,91,94,98,105,123,145,149],"latent":[19,48,102],"representation":[20],"decomposed":[22],"into":[23],"several":[24],"parts":[25],"that":[26,50,117],"correspond":[27],"to":[28,100],"different":[29,37],"scales.":[30],"The":[31,78],"model":[32],"consists":[33],"of":[34,42,47,93],"three":[35],"functionally":[36],"components.":[38],"First,":[39],"a":[40,45,67,74,131],"stack":[41],"encoders":[43],"generates":[44],"set":[46],"vectors":[49,103,112],"contain":[51],"information":[52],"from":[53,73,148],"an":[54],"increasingly":[55],"larger":[56],"receptive":[57],"field.":[58],"Second,":[59],"decoders":[61],"construct":[62],"clean":[64],"speech":[65,125],"stage-wise":[68],"and":[69,97,127,134],"additive":[70],"fashion,":[71],"starting":[72],"learned":[75],"initial":[76,111],"vector.":[77],"third":[79],"component,":[80],"we":[82],"call":[83],"funnel":[84],"networks,":[85],"tasked":[87],"with":[88],"\"knitting\"":[89],"together":[90],"outputs":[92],"previous":[95],"decoder":[96],"encoder":[99],"compute":[101],"for":[104,110,122],"next":[106],"decoder.":[107],"Several":[108],"options":[109],"are":[113,142],"explored.":[114],"Experiments":[115],"show":[116],"achieves":[119],"significant":[120],"improvements":[121],"considered":[124],"quality":[126],"intelligibility":[128],"measures,":[129],"outperforming":[130],"denoising":[132],"other":[135],"step-wise":[136],"models.":[137],"Furthermore,":[138],"its":[139],"internal":[140],"workings":[141],"investigated":[143],"using":[144],"intermediate":[146],"results":[147],"decoders.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}