{"id":"https://openalex.org/W2937829825","doi":"https://doi.org/10.1109/icassp.2019.8683398","title":"Speech Waveform Reconstruction Using Convolutional Neural Networks with Noise and Periodic Inputs","display_name":"Speech Waveform Reconstruction Using Convolutional Neural Networks with Noise and Periodic Inputs","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937829825","doi":"https://doi.org/10.1109/icassp.2019.8683398","mag":"2937829825"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"id":"https://openalex.org/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185658715"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":null,"first_page":"7045","last_page":"7049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9898999929428101,"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/waveform","display_name":"Waveform","score":0.8613681197166443},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.8447661399841309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8094288110733032},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6340785026550293},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5655630826950073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5211886763572693},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47935134172439575},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42571133375167847},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35505127906799316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3407270312309265},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11461925506591797}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8613681197166443},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8447661399841309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8094288110733032},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6340785026550293},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5655630826950073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5211886763572693},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47935134172439575},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42571133375167847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35505127906799316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407270312309265},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11461925506591797},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/5c268e7a-5f04-4b35-8866-ecc3d45ba5c8","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/5c268e7a-5f04-4b35-8866-ecc3d45ba5c8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7898478334","display_name":null,"funder_award_id":"EP/P011586/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2120847449","https://openalex.org/W2126942983","https://openalex.org/W2129142580","https://openalex.org/W2146324387","https://openalex.org/W2194775991","https://openalex.org/W2402144811","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2559246505","https://openalex.org/W2561907692","https://openalex.org/W2584032004","https://openalex.org/W2598638573","https://openalex.org/W2749609415","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2786868129","https://openalex.org/W2803714261","https://openalex.org/W2888804509","https://openalex.org/W2890983311","https://openalex.org/W2949382160","https://openalex.org/W2953384591","https://openalex.org/W2963782041","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4298642009","https://openalex.org/W6603838645","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6713134421","https://openalex.org/W6730741096","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6844105982"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W2281134365","https://openalex.org/W4310746709","https://openalex.org/W4385574037","https://openalex.org/W4386075645","https://openalex.org/W2964954556"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,9,15,21,28,36,76,92,117,123],"method":[4],"for":[5,87],"upsampling":[6],"and":[7,35,41,69,106,119,126,135],"transforming":[8],"compact":[10],"representation":[11],"of":[12,73,101],"acoustics":[13],"into":[14],"corresponding":[16],"speech":[17],"waveform.":[18],"Similar":[19],"to":[20,44,57,138,142],"conventional":[22,102],"vocoder,":[23],"the":[24,48,52,59,62,71,81,84],"proposed":[25,63],"system":[26,64],"takes":[27],"pulse":[29],"train":[30],"derived":[31],"from":[32,67],"fundamental":[33],"frequency":[34],"noise":[37],"sequence":[38],"as":[39],"inputs":[40],"shapes":[42],"them":[43],"be":[45,143],"consistent":[46],"with":[47,99],"acoustic":[49],"features.":[50],"However,":[51],"filters":[53],"that":[54,100],"are":[55,65],"used":[56],"shape":[58],"waveform":[60,89],"in":[61,75,91,116],"learned":[66],"data,":[68],"take":[70],"form":[72],"layers":[74],"convolutional":[77],"neural":[78],"network.":[79],"Because":[80],"network":[82],"performs":[83],"transformation":[85],"simultaneously":[86],"all":[88],"samples":[90],"sentence,":[93],"its":[94],"synthesis":[95],"speed":[96],"is":[97,113],"comparable":[98],"vocoders":[103],"on":[104,110],"CPU,":[105],"many":[107],"times":[108],"faster":[109],"GPU.":[111],"It":[112],"trained":[114],"directly":[115],"fast":[118],"straightforward":[120],"manner,":[121],"using":[122],"combined":[124],"time-":[125],"frequency-domain":[127],"objective":[128],"function.":[129],"We":[130],"use":[131],"publicly":[132],"available":[133],"data":[134],"provide":[136],"code":[137],"allow":[139],"our":[140],"results":[141],"reproduced.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}