{"id":"https://openalex.org/W4394635172","doi":"https://doi.org/10.48550/arxiv.2005.11704","title":"MIMO Speech Compression and Enhancement Based on Convolutional Denoising Autoencoder","display_name":"MIMO Speech Compression and Enhancement Based on Convolutional Denoising Autoencoder","publication_year":2020,"publication_date":"2020-05-24","ids":{"openalex":"https://openalex.org/W4394635172","doi":"https://doi.org/10.48550/arxiv.2005.11704"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2005.11704","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11704","pdf_url":"https://arxiv.org/pdf/2005.11704","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.11704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110692834","display_name":"You-Jin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, You-Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521","observed_orcids":["https://orcid.org/0000-0002-2652-5521"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Syu-Siang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418","observed_orcids":["https://orcid.org/0000-0001-6956-0418"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsao, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015868237","display_name":"Borching Su","orcid":"https://orcid.org/0000-0001-8617-2601","observed_orcids":["https://orcid.org/0000-0001-8617-2601"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Borching","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0010000000474974513,"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/T10688","display_name":"Image and Signal Denoising Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-coding","display_name":"speech coding","score":0.7889999747276306},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.9980000257492065},{"id":"https://openalex.org/keywords/mimo","display_name":"MIMO","score":0.7009999752044678},{"id":"https://openalex.org/keywords/convolutional-denoising-autoencoder","display_name":"convolutional denoising autoencoder","score":0.9980000257492065},{"id":"https://openalex.org/keywords/fully-convolutional-network","display_name":"fully convolutional network","score":0.8149999976158142},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.7699999809265137},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.5550000071525574},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532622814178467},{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.7296781539916992},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5748129487037659},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4883820414543152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4699416756629944},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.44394952058792114},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4274532198905945},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4122842848300934},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.4108264744281769},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.33119094371795654},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.305056095123291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.302964985370636},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17354929447174072},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2005.11704","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11704","pdf_url":"https://arxiv.org/pdf/2005.11704","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2005.11704","doi":"https://doi.org/10.48550/arxiv.2005.11704","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.11704","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.11704","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11704","pdf_url":"https://arxiv.org/pdf/2005.11704","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4943999946117401,"id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3027119780","https://openalex.org/W4415433559","https://openalex.org/W4400908489","https://openalex.org/W2966854058","https://openalex.org/W2940247716","https://openalex.org/W4321062218","https://openalex.org/W7155045133","https://openalex.org/W3217670778","https://openalex.org/W3035935937","https://openalex.org/W2972992323"],"abstract_inverted_index":{"For":[0],"speech-related":[1],"applications":[2,76],"in":[3,19,75,104],"IoT":[4],"environments,":[5],"identifying":[6],"effective":[7],"methods":[8],"to":[9,23,50,83],"handle":[10,78],"interference":[11],"noises":[12],"and":[13,38,55,66,96,120],"compress":[14],"the":[15,57,101,112,124],"amount":[16,125],"of":[17,59,126,132],"data":[18,128],"transmissions":[20],"is":[21],"essential":[22],"achieve":[24],"high-quality":[25],"services.":[26],"In":[27],"this":[28],"study,":[29],"we":[30],"propose":[31],"a":[32,44,91,97,130],"novel":[33],"multi-input":[34,67],"multi-output":[35],"speech":[36,53,118],"compression":[37],"enhancement":[39],"(MIMO-SCE)":[40],"system":[41],"based":[42],"on":[43],"convolutional":[45,93],"denoising":[46],"autoencoder":[47],"(CDAE)":[48],"model":[49],"simultaneously":[51],"improve":[52],"quality":[54,119],"reduce":[56],"dimensions":[58],"transmission":[60],"data.":[61],"Compared":[62],"with":[63],"conventional":[64],"single-channel":[65],"single-output":[68],"systems,":[69],"MIMO":[70,105],"systems":[71],"can":[72],"be":[73,84],"employed":[74],"that":[77,111],"multiple":[79],"acoustic":[80],"signals":[81],"need":[82],"handled.":[85],"We":[86],"investigated":[87],"two":[88],"CDAE":[89],"models,":[90],"fully":[92],"network":[94],"(FCN)":[95],"Sinc":[98],"FCN,":[99],"as":[100],"core":[102],"models":[103],"systems.":[106],"The":[107],"experimental":[108],"results":[109],"confirm":[110],"proposed":[113],"MIMO-SCE":[114],"framework":[115],"effectively":[116],"improves":[117],"intelligibility":[121],"while":[122],"reducing":[123],"recording":[127],"by":[129],"factor":[131],"7":[133],"for":[134],"transmission.":[135]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-04-10T00:00:00"}