{"id":"https://openalex.org/W2761952131","doi":"https://doi.org/10.1109/taslp.2017.2761236","title":"Artificial Speech Bandwidth Extension Using Deep Neural Networks for Wideband Spectral Envelope Estimation","display_name":"Artificial Speech Bandwidth Extension Using Deep Neural Networks for Wideband Spectral Envelope Estimation","publication_year":2017,"publication_date":"2017-10-09","ids":{"openalex":"https://openalex.org/W2761952131","doi":"https://doi.org/10.1109/taslp.2017.2761236","mag":"2761952131"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2761236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2761236","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5062346765","display_name":"Johannes Abel","orcid":"https://orcid.org/0000-0003-3675-3488"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Abel","raw_affiliation_strings":["Institute for Communications Technology, Techni-sche Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Techni-sche Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["Institute for Communications Technology, Techni-sche Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Techni-sche Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062346765"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":4.993,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96349962,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"1","first_page":"71","last_page":"83"},"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/wideband-audio","display_name":"Wideband audio","score":0.7629351615905762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7200925350189209},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.717610776424408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6866235136985779},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.6431522369384766},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6208357810974121},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.58536297082901},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5747255682945251},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.5634159445762634},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.52353835105896},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4854777157306671},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4791538119316101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319016933441162},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3881518244743347},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32727742195129395},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2578867971897125},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10830685496330261},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10769259929656982},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.0992383360862732},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08611756563186646},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.08048754930496216}],"concepts":[{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.7629351615905762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7200925350189209},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.717610776424408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866235136985779},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.6431522369384766},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6208357810974121},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.58536297082901},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5747255682945251},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.5634159445762634},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.52353835105896},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4854777157306671},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4791538119316101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319016933441162},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3881518244743347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32727742195129395},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2578867971897125},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10830685496330261},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10769259929656982},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0992383360862732},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08611756563186646},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.08048754930496216},{"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},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2761236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2761236","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1517841224","https://openalex.org/W1547915404","https://openalex.org/W1576278180","https://openalex.org/W1578856370","https://openalex.org/W1624062987","https://openalex.org/W1635512741","https://openalex.org/W1663056653","https://openalex.org/W1923007241","https://openalex.org/W1966264494","https://openalex.org/W1985029311","https://openalex.org/W2004018702","https://openalex.org/W2014962887","https://openalex.org/W2022554507","https://openalex.org/W2035859817","https://openalex.org/W2070450685","https://openalex.org/W2074192013","https://openalex.org/W2100285470","https://openalex.org/W2101490115","https://openalex.org/W2107878631","https://openalex.org/W2116878849","https://openalex.org/W2150307270","https://openalex.org/W2160815625","https://openalex.org/W2161965203","https://openalex.org/W2167341025","https://openalex.org/W2171815504","https://openalex.org/W2182920677","https://openalex.org/W2397254463","https://openalex.org/W2397839461","https://openalex.org/W2400295372","https://openalex.org/W2400346108","https://openalex.org/W2400697507","https://openalex.org/W2400830530","https://openalex.org/W2401383940","https://openalex.org/W2402768323","https://openalex.org/W2518315489","https://openalex.org/W2536224642","https://openalex.org/W2557283755","https://openalex.org/W2557745710","https://openalex.org/W2799061466","https://openalex.org/W3127686677","https://openalex.org/W3217664684","https://openalex.org/W4232545299","https://openalex.org/W4244494905","https://openalex.org/W6601785968","https://openalex.org/W6636993980","https://openalex.org/W6677155281","https://openalex.org/W6686034693","https://openalex.org/W6712662408","https://openalex.org/W6713030564","https://openalex.org/W6804204384","https://openalex.org/W6990954807"],"related_works":["https://openalex.org/W2152250293","https://openalex.org/W3150049111","https://openalex.org/W2162700463","https://openalex.org/W3135807828","https://openalex.org/W2158843472","https://openalex.org/W2101490115","https://openalex.org/W1987295223","https://openalex.org/W2110311073","https://openalex.org/W2034562896","https://openalex.org/W2592346140"],"abstract_inverted_index":{"Estimating":[0],"a":[1,12,37,85,105,136,144],"wideband":[2,66,127],"spectral":[3,67],"envelope":[4],"having":[5],"only":[6],"narrowband":[7,154],"speech":[8,30,98,155],"at":[9],"hand":[10],"is":[11,90],"challenging":[13],"task.":[14],"In":[15,77],"this":[16],"paper,":[17],"we":[18,47,83],"explore":[19],"ways":[20],"to":[21,62,73,79,93],"do":[22],"so":[23],"in":[24],"the":[25,74,94,115,148],"context":[26],"of":[27,51,57,65,147,156],"an":[28],"artificial":[29],"bandwidth":[31],"extension":[32],"(ABE)":[33],"framework.":[34],"Starting":[35],"from":[36],"typical":[38],"hidden":[39],"Markov":[40],"model":[41,44],"(HMM)/Gaussian":[42],"mixture":[43],"baseline":[45],"scheme,":[46],"investigate":[48],"two":[49],"types":[50],"features,":[52],"topologies,":[53],"and":[54,96,135],"regularization":[55],"approaches":[56],"deep":[58],"neural":[59],"networks":[60],"(DNNs)":[61],"obtain":[63],"estimates":[64],"envelopes":[68],"with":[69],"smallest":[70],"cepstral":[71],"distance":[72,121],"original":[75],"ones.":[76],"order":[78],"draw":[80],"realistic":[81],"conclusions,":[82],"employ":[84],"database":[86],"for":[87],"test,":[88],"which":[89],"acoustically":[91],"different":[92],"training":[95],"validation":[97],"material.":[99],"Interestingly,":[100],"it":[101],"turns":[102],"out":[103],"that":[104],"DNN":[106,150],"regression":[107],"approach":[108,152],"outperforms":[109],"all":[110],"other":[111],"investigated":[112],"methods,":[113],"although":[114],"HMM":[116],"has":[117],"been":[118],"dropped.":[119],"Cepstral":[120],"was":[122,129],"reduced":[123],"by":[124,131],"1.18":[125],"dB,":[126],"PESQ":[128],"improved":[130],"0.23":[132],"MOS":[133],"points,":[134],"subjective":[137],"comparison":[138],"category":[139],"rating":[140],"listening":[141],"test":[142],"showed":[143],"significant":[145],"preference":[146],"best":[149],"ABE":[151],"versus":[153],"1.37":[157],"CMOS":[158],"points.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}