{"id":"https://openalex.org/W2948125348","doi":"https://doi.org/10.1109/access.2019.2920663","title":"DeepVoCoder: A CNN Model for Compression and Coding of Narrow Band Speech","display_name":"DeepVoCoder: A CNN Model for Compression and Coding of Narrow Band Speech","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948125348","doi":"https://doi.org/10.1109/access.2019.2920663","mag":"2948125348"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2920663","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2920663","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730308.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730308.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071978946","display_name":"Hacer Yal\u0131m Kele\u015f","orcid":"https://orcid.org/0000-0002-1671-4126"},"institutions":[{"id":"https://openalex.org/I149218525","display_name":"Ankara University","ror":"https://ror.org/01wntqw50","country_code":"TR","type":"education","lineage":["https://openalex.org/I149218525"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hacer Yalim Keles","raw_affiliation_strings":["Computer Engineering Department, Ankara University, Ankara, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Ankara University, Ankara, Turkey","institution_ids":["https://openalex.org/I149218525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027306294","display_name":"Jan Rozhon","orcid":"https://orcid.org/0000-0003-4768-6073"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Rozhon","raw_affiliation_strings":["Department of Telecommunications, VSB\u2013Technical University of Ostrava, Ostrava, Czech Republic","Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB&#x2013;Technical University of Ostrava, Ostrava, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications, VSB\u2013Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]},{"raw_affiliation_string":"Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB&#x2013;Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018593379","display_name":"Hakk\u0131 G\u00f6khan \u0130lk","orcid":"https://orcid.org/0000-0003-4365-8286"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"H. Gokhan Ilk","raw_affiliation_strings":["IT4 Innovations, VSB\u2013Technical University of Ostrava, Ostrava, Czech Republic","ORCiD","IT4 Innovations, VSB&#x2013;Technical University of Ostrava, Ostrava, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-4365-8286","affiliations":[{"raw_affiliation_string":"IT4 Innovations, VSB\u2013Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]},{"raw_affiliation_string":"ORCiD","institution_ids":[]},{"raw_affiliation_string":"IT4 Innovations, VSB&#x2013;Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072201492","display_name":"Miroslav Vozn\u0306\u00e1k","orcid":"https://orcid.org/0000-0001-5135-7980"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Miroslav Voznak","raw_affiliation_strings":["Department of Telecommunications, VSB\u2013Technical University of Ostrava, Ostrava, Czech Republic","Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB&#x2013;Technical University of Ostrava, Ostrava, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications, VSB\u2013Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]},{"raw_affiliation_string":"Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB&#x2013;Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.501,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.62506086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"75081","last_page":"75089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8398728966712952},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.742416262626648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7119535207748413},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.6202611327171326},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6182534098625183},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5778915882110596},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5441253781318665},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.5431231260299683},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.5093854069709778},{"id":"https://openalex.org/keywords/full-rate","display_name":"Full Rate","score":0.4839616119861603},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.451521098613739},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.4284954071044922},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4247782826423645},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4083956480026245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2511010766029358},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1909818947315216},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.189335435628891},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.0917879045009613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8398728966712952},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.742416262626648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7119535207748413},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.6202611327171326},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6182534098625183},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5778915882110596},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5441253781318665},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.5431231260299683},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.5093854069709778},{"id":"https://openalex.org/C197477341","wikidata":"https://www.wikidata.org/wiki/Q2532845","display_name":"Full Rate","level":3,"score":0.4839616119861603},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.451521098613739},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.4284954071044922},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4247782826423645},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4083956480026245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2511010766029358},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1909818947315216},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.189335435628891},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0917879045009613},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2019.2920663","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2920663","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730308.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7fd2cf696ed244fbb62dbb7bbdc4d4fc","is_oa":true,"landing_page_url":"https://doaj.org/article/7fd2cf696ed244fbb62dbb7bbdc4d4fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 75081-75089 (2019)","raw_type":"article"},{"id":"pmh:oai:dspace.vsb.cz:10084/138509","is_oa":false,"landing_page_url":"http://hdl.handle.net/10084/138509","pdf_url":null,"source":{"id":"https://openalex.org/S4306401668","display_name":"DSpace V\u0160B-TUO (V\u0160B-TUO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142208455","host_organization_name":"VSB - Technical University of Ostrava","host_organization_lineage":["https://openalex.org/I142208455"],"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":"Peer-reviewed"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2920663","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2920663","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730308.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324050","display_name":"Ostravsk\u00e1 Univerzita v Ostrav\u011b","ror":"https://ror.org/00pyqav47"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948125348.pdf","grobid_xml":"https://content.openalex.org/works/W2948125348.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1496971974","https://openalex.org/W1497265063","https://openalex.org/W1522301498","https://openalex.org/W1608472120","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1905882502","https://openalex.org/W1990992471","https://openalex.org/W2009674825","https://openalex.org/W2037034710","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2108532241","https://openalex.org/W2134383396","https://openalex.org/W2151626637","https://openalex.org/W2159644785","https://openalex.org/W2164764235","https://openalex.org/W2326507777","https://openalex.org/W2519091744","https://openalex.org/W2749651610","https://openalex.org/W2775336875","https://openalex.org/W2783946051","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W6629867248","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6639824700","https://openalex.org/W6746756656"],"related_works":["https://openalex.org/W72173219","https://openalex.org/W2060409740","https://openalex.org/W2113878160","https://openalex.org/W2115236569","https://openalex.org/W1578591928","https://openalex.org/W2139929615","https://openalex.org/W2042028224","https://openalex.org/W1662217694","https://openalex.org/W1968385191","https://openalex.org/W1932653299"],"abstract_inverted_index":{"This":[0,119],"paper":[1,120],"proposes":[2],"a":[3,54],"convolutional":[4,57],"neural":[5],"network":[6],"(CNN)-based":[7],"encoder":[8,83],"model":[9,23,42],"to":[10,69,106],"compress":[11],"and":[12,38,50,87,128,138,145],"code":[13],"speech":[14,27,46,73,92,110,136],"signal":[15,111],"directly":[16],"from":[17],"raw":[18],"input":[19],"speech.":[20],"Although":[21],"the":[22,71,81,91,108,116,123,153],"can":[24],"synthesize":[25],"wideband":[26],"by":[28,74],"implicit":[29],"bandwidth":[30],"extension,":[31],"narrowband":[32],"is":[33,64,98,104],"preferred":[34],"for":[35,134],"IP":[36],"telephony":[37],"telecommunications":[39],"purposes.":[40],"The":[41,76,140],"takes":[43],"time":[44],"domain":[45],"samples":[47],"as":[48],"inputs":[49],"encodes":[51],"them":[52],"using":[53,115],"cascade":[55],"of":[56,80,90,126],"filters":[58],"in":[59,112,152],"multiple":[60],"layers,":[61],"where":[62],"pooling":[63],"applied":[65],"after":[66],"some":[67],"layers":[68],"downsample":[70],"encoded":[72],"half.":[75],"final":[77],"bottleneck":[78],"layer":[79],"CNN":[82,117,130],"provides":[84],"an":[85],"abstract":[86],"compact":[88,102],"representation":[89,103],"signal.":[93],"In":[94],"this":[95,101],"paper,":[96],"it":[97],"demonstrated":[99],"that":[100],"sufficient":[105],"reconstruct":[107],"original":[109],"high":[113],"quality":[114,149],"decoder.":[118],"also":[121],"discusses":[122],"theoretical":[124],"background":[125],"why":[127],"how":[129],"may":[131],"be":[132],"used":[133],"end-to-end":[135],"compression":[137],"coding.":[139],"complexity,":[141],"delay,":[142],"memory":[143],"requirements,":[144],"bit":[146],"rate":[147],"versus":[148],"are":[150],"discussed":[151],"experimental":[154],"results.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-10T00:00:00"}
