{"id":"https://openalex.org/W4372328998","doi":"https://doi.org/10.1109/icassp49357.2023.10094729","title":"PUFFIN: Pitch-Synchronous Neural Waveform Generation for Fullband Speech on Modest Devices","display_name":"PUFFIN: Pitch-Synchronous Neural Waveform Generation for Fullband Speech on Modest Devices","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372328998","doi":"https://doi.org/10.1109/icassp49357.2023.10094729"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094729","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/files/332119668/Puffin_Pitch_Sync_WATTS_DOA15022023_AFV_CC_BY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"id":"https://openalex.org/I3206020590","display_name":"ProQuest (United States)","ror":"https://ror.org/039swsa61","country_code":"US","type":"company","lineage":["https://openalex.org/I3206020590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["SpeakUnique Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakUnique Ltd","institution_ids":["https://openalex.org/I3206020590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041594839","display_name":"Lovisa Wihlborg","orcid":null},"institutions":[{"id":"https://openalex.org/I3206020590","display_name":"ProQuest (United States)","ror":"https://ror.org/039swsa61","country_code":"US","type":"company","lineage":["https://openalex.org/I3206020590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lovisa Wihlborg","raw_affiliation_strings":["SpeakUnique Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakUnique Ltd","institution_ids":["https://openalex.org/I3206020590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I3206020590","display_name":"ProQuest (United States)","ror":"https://ror.org/039swsa61","country_code":"US","type":"company","lineage":["https://openalex.org/I3206020590"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["SpeakUnique Ltd","CSTR, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakUnique Ltd","institution_ids":["https://openalex.org/I3206020590"]},{"raw_affiliation_string":"CSTR, University of Edinburgh, UK","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":3,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8093376159667969},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7020710706710815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6280539035797119},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4807312488555908},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.47392329573631287},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09548282623291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8093376159667969},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7020710706710815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6280539035797119},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4807312488555908},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.47392329573631287},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09548282623291016},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094729","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/fb3a6704-4d4c-4917-90fa-bdec2edf1af3","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/332119668/Puffin_Pitch_Sync_WATTS_DOA15022023_AFV_CC_BY.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/fb3a6704-4d4c-4917-90fa-bdec2edf1af3","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/fb3a6704-4d4c-4917-90fa-bdec2edf1af3","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/fb3a6704-4d4c-4917-90fa-bdec2edf1af3","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/332119668/Puffin_Pitch_Sync_WATTS_DOA15022023_AFV_CC_BY.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2749609415","https://openalex.org/W2769810959","https://openalex.org/W2956105671","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2990440871","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W3095419383","https://openalex.org/W4221055745","https://openalex.org/W4221152438","https://openalex.org/W4294619240","https://openalex.org/W4372318157","https://openalex.org/W6732429163","https://openalex.org/W6767111847","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2514064218","https://openalex.org/W2132658536","https://openalex.org/W2094188777","https://openalex.org/W2112609279","https://openalex.org/W1581825163","https://openalex.org/W1483316057","https://openalex.org/W2039489009","https://openalex.org/W2366310385","https://openalex.org/W2399404538","https://openalex.org/W2061937230"],"abstract_inverted_index":{"We":[0,98],"present":[1,99],"a":[2,86,93,102],"neural":[3,46],"vocoder":[4],"designed":[5],"with":[6,22,85],"low-powered":[7],"Alternative":[8],"and":[9,63],"Augmentative":[10],"Communication":[11],"devices":[12,44],"in":[13],"mind.":[14],"By":[15],"combining":[16],"elements":[17],"of":[18,29,95,101,110],"successful":[19],"modern":[20],"vocoders":[21,47],"established":[23],"ideas":[24],"from":[25],"an":[26,108],"older":[27],"generation":[28],"technology,":[30],"our":[31],"system":[32,53,81,111],"is":[33,54],"able":[34],"to":[35,76],"produce":[36],"high":[37],"quality":[38,84],"synthetic":[39],"speech":[40,78],"at":[41],"48kHz":[42],"on":[43,68],"where":[45],"are":[48],"otherwise":[49],"prohibitively":[50],"complex.":[51],"The":[52],"trained":[55],"adversarially":[56],"using":[57,91],"differentiable":[58],"pitch":[59,69],"synchronous":[60,70],"overlap":[61],"add,":[62],"reduces":[64],"complexity":[65],"by":[66],"relying":[67],"Inverse":[71],"Short-Time":[72],"Fourier":[73],"Transform":[74],"(ISTFT)":[75],"generate":[77],"samples.":[79],"Our":[80],"achieves":[82],"comparable":[83],"strong":[87],"baseline":[88],"(HiFi-GAN)":[89],"while":[90],"only":[92],"fraction":[94],"the":[96],"compute.":[97],"results":[100],"perceptual":[103],"evaluation":[104],"as":[105,107],"well":[106],"analysis":[109],"complexity.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}