{"id":"https://openalex.org/W3015837673","doi":"https://doi.org/10.1109/icassp40776.2020.9054551","title":"Time-Domain Neural Network Approach for Speech Bandwidth Extension","display_name":"Time-Domain Neural Network Approach for Speech Bandwidth Extension","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015837673","doi":"https://doi.org/10.1109/icassp40776.2020.9054551","mag":"3015837673"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5102005971","display_name":"Xiang Hao","orcid":"https://orcid.org/0000-0003-4828-3938"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Hao","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001511287","display_name":"Nana Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nana Hou","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102005971"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.3638,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80770244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":0.9994000196456909,"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":0.9994000196456909,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9927999973297119,"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":0.9897000193595886,"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/pesq","display_name":"PESQ","score":0.93426114320755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803782224655151},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6153020858764648},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.5963194966316223},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5876522064208984},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5473287105560303},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4558892846107483},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.428358793258667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42556142807006836},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42165809869766235},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3587130010128021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3333582282066345},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23117324709892273},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.13868990540504456},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1268671154975891}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.93426114320755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803782224655151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6153020858764648},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.5963194966316223},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5876522064208984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5473287105560303},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4558892846107483},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.428358793258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42556142807006836},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42165809869766235},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3587130010128021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3333582282066345},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23117324709892273},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.13868990540504456},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1268671154975891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1485515796","https://openalex.org/W1517841224","https://openalex.org/W1522137499","https://openalex.org/W1531967940","https://openalex.org/W1971868317","https://openalex.org/W1994997782","https://openalex.org/W2099471712","https://openalex.org/W2100285470","https://openalex.org/W2128767958","https://openalex.org/W2135567392","https://openalex.org/W2147152002","https://openalex.org/W2397254463","https://openalex.org/W2399742709","https://openalex.org/W2400830530","https://openalex.org/W2404938947","https://openalex.org/W2518315489","https://openalex.org/W2519091744","https://openalex.org/W2603567530","https://openalex.org/W2748163399","https://openalex.org/W2761952131","https://openalex.org/W2784918340","https://openalex.org/W2802034954","https://openalex.org/W2889905534","https://openalex.org/W2890648862","https://openalex.org/W2892335023","https://openalex.org/W2892365986","https://openalex.org/W2894295011","https://openalex.org/W2916798096","https://openalex.org/W2935953376","https://openalex.org/W2939253202","https://openalex.org/W2940120659","https://openalex.org/W2940290905","https://openalex.org/W2944438111","https://openalex.org/W2962780374","https://openalex.org/W2962879692","https://openalex.org/W2963341071","https://openalex.org/W2963519193","https://openalex.org/W2963952344","https://openalex.org/W3122318757","https://openalex.org/W4295521014","https://openalex.org/W4297817572","https://openalex.org/W4320013936","https://openalex.org/W6629271464","https://openalex.org/W6679997972","https://openalex.org/W6682013673","https://openalex.org/W6712300757","https://openalex.org/W6713030564","https://openalex.org/W6735429107","https://openalex.org/W6735913928","https://openalex.org/W6741681139","https://openalex.org/W6744578475","https://openalex.org/W6754743415","https://openalex.org/W6755257315","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"the":[5,28,33,37,52,66,73,105,113,116],"time-domain":[6,61,117],"neural":[7,22],"network":[8,17,23,53,70,108],"approach":[9],"for":[10],"speech":[11,82],"bandwidth":[12],"extension.":[13],"We":[14,45],"propose":[15,46],"a":[16,47,55],"architecture,":[18],"named":[19],"multi-scale":[20,68,106],"fusion":[21,69,107],"(MfNet),":[24],"that":[25],"gradually":[26],"restores":[27],"low-frequency":[29],"signal":[30,35,85,90],"and":[31,60,98],"predicts":[32],"high-frequency":[34],"through":[36],"exchange":[38],"of":[39,57,78,81,112,115],"information":[40],"across":[41],"different":[42],"scale":[43],"representations.":[44],"training":[48],"scheme":[49],"to":[50,86,91],"optimize":[51],"with":[54],"combination":[56],"perceptual":[58,79],"loss":[59],"adversarial":[62],"loss.":[63],"Experiments":[64],"show":[65],"proposed":[67],"consistently":[71],"outperforms":[72],"competing":[74],"methods":[75],"in":[76],"terms":[77],"evaluation":[80],"quality":[83],"(PESQ),":[84],"distortion":[87],"rate":[88,101],"(SDR),":[89],"noise":[92],"ratio":[93],"(SNR),":[94],"log-spectral":[95],"distance":[96],"(LSD)":[97],"word":[99],"error":[100],"(WER).":[102],"More":[103],"promisingly,":[104],"requires":[109],"only":[110],"10%":[111],"parameters":[114],"reference":[118],"baseline.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}