{"id":"https://openalex.org/W4372318157","doi":"https://doi.org/10.1109/icassp49357.2023.10095729","title":"Autovocoder: Fast Waveform Generation from a Learned Speech Representation Using Differentiable Digital Signal Processing","display_name":"Autovocoder: Fast Waveform Generation from a Learned Speech Representation Using Differentiable Digital Signal Processing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372318157","doi":"https://doi.org/10.1109/icassp49357.2023.10095729"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/0be09a4b-1f01-4bd7-9c37-af2aabe78342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064983567","display_name":"Jacob J Webber","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jacob J Webber","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"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/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108824343","display_name":"Evelyn Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Evelyn Williams","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music, and Hearing,Stockholm,Sweden","Division of Speech, Music, and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music, and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music, and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"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/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9411609172821045},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.8038552403450012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373945713043213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6694534420967102},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.5380297303199768},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4549746513366699},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.44888392090797424},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41177552938461304},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4027680456638336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3898577392101288},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32381802797317505},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.18788206577301025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10740792751312256},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08044540882110596},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.07333749532699585},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.06832468509674072}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9411609172821045},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8038552403450012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373945713043213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6694534420967102},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.5380297303199768},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4549746513366699},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.44888392090797424},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41177552938461304},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4027680456638336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3898577392101288},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32381802797317505},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.18788206577301025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10740792751312256},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08044540882110596},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.07333749532699585},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.06832468509674072},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/0be09a4b-1f01-4bd7-9c37-af2aabe78342","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0be09a4b-1f01-4bd7-9c37-af2aabe78342","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/0be09a4b-1f01-4bd7-9c37-af2aabe78342","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/10095729","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/0be09a4b-1f01-4bd7-9c37-af2aabe78342","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/332111864/Autovocoder_WEBBER_DOA15022023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/0be09a4b-1f01-4bd7-9c37-af2aabe78342","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0be09a4b-1f01-4bd7-9c37-af2aabe78342","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2025768430","https://openalex.org/W2097775139","https://openalex.org/W2120847449","https://openalex.org/W2191779130","https://openalex.org/W2519091744","https://openalex.org/W2749609415","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2946200149","https://openalex.org/W2963091184","https://openalex.org/W2964243274","https://openalex.org/W2990440871","https://openalex.org/W3034949308","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3095448311","https://openalex.org/W3100270690","https://openalex.org/W3150572638","https://openalex.org/W3163845842","https://openalex.org/W3169905056","https://openalex.org/W3215615641","https://openalex.org/W4221152438","https://openalex.org/W4226132755","https://openalex.org/W4294619240","https://openalex.org/W4295312788","https://openalex.org/W4297841714","https://openalex.org/W4298580827","https://openalex.org/W4372328998","https://openalex.org/W6748409065","https://openalex.org/W6763832098","https://openalex.org/W6766978945","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3210733254"],"abstract_inverted_index":{"Most":[0],"state-of-the-art":[1],"Text-to-Speech":[2],"systems":[3],"use":[4,56],"the":[5,13,25,65,85,96,105,118,127],"mel-spectrogram":[6,21,40],"as":[7],"an":[8],"intermediate":[9],"representation,":[10],"to":[11,59,73,115,124],"decompose":[12],"task":[14],"into":[15],"acoustic":[16],"modelling":[17],"and":[18,67,100],"waveform":[19,26,37,75,91],"generation.A":[20],"is":[22,120],"extracted":[23],"from":[24,38],"by":[27],"a":[28,35,39,46,61,74,81,90],"simple,":[29,77],"fast":[30,78],"DSP":[31],"operation,":[32],"but":[33],"generating":[34],"high-quality":[36],"requires":[41],"computationally":[42],"expensive":[43],"machine":[44,57],"learning:":[45],"neural":[47,106],"vocoder.":[48],"Our":[49],"proposed":[50],"\"autovocoder\"":[51],"reverses":[52],"this":[53],"arrangement.":[54],"We":[55,109],"learning":[58],"obtain":[60],"representation":[62],"that":[63,68,117],"replaces":[64],"mel-spectrogram,":[66],"can":[69],"be":[70],"inverted":[71],"back":[72],"using":[76],"operations":[79],"including":[80],"differentiable":[82],"implementation":[83],"of":[84,121],"inverse":[86],"STFT.The":[87],"autovocoder":[88],"generates":[89],"5":[92],"times":[93,102],"faster":[94,103],"than":[95,104],"DSP-based":[97],"Griffin-Lim":[98],"algorithm,":[99],"14":[101],"vocoder":[107],"HiFi-GAN.":[108],"provide":[110],"perceptual":[111],"listening":[112],"test":[113],"results":[114],"confirm":[116],"speech":[119],"comparable":[122],"quality":[123],"HiFi-GAN":[125],"in":[126],"copy":[128],"synthesis":[129],"task.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2023-05-07T00:00:00"}
