{"id":"https://openalex.org/W2890983311","doi":"https://doi.org/10.1109/icassp.2018.8462431","title":"Fftnet: A Real-Time Speaker-Dependent Neural Vocoder","display_name":"Fftnet: A Real-Time Speaker-Dependent Neural Vocoder","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890983311","doi":"https://doi.org/10.1109/icassp.2018.8462431","mag":"2890983311"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044614923","display_name":"Gautham J. Mysore","orcid":"https://orcid.org/0000-0003-0483-9252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham J. Mysore","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085050428","display_name":"Jingwan Lu","orcid":"https://orcid.org/0000-0002-3598-9918"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwan Lu","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2251","last_page":"2255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.818597674369812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8090114593505859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7212150692939758},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6505776047706604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.539625346660614},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5094810128211975},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.485434353351593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4804691672325134},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10649475455284119}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.818597674369812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090114593505859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7212150692939758},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6505776047706604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.539625346660614},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5094810128211975},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.485434353351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4804691672325134},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10649475455284119},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W573259127","https://openalex.org/W1495679096","https://openalex.org/W1510007267","https://openalex.org/W1522301498","https://openalex.org/W2061171222","https://openalex.org/W2141708418","https://openalex.org/W2145892079","https://openalex.org/W2251498782","https://openalex.org/W2328165521","https://openalex.org/W2395718496","https://openalex.org/W2402356521","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2604184139","https://openalex.org/W2606176153","https://openalex.org/W2737697117","https://openalex.org/W2746474733","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2901997113","https://openalex.org/W2963103134","https://openalex.org/W3142087749","https://openalex.org/W4230964063","https://openalex.org/W4253928870","https://openalex.org/W4294619240","https://openalex.org/W4298642009","https://openalex.org/W6603838645","https://openalex.org/W6712900185","https://openalex.org/W6736356763","https://openalex.org/W6740049204","https://openalex.org/W6756197946","https://openalex.org/W6792025129","https://openalex.org/W6950332740"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973","https://openalex.org/W2039489009","https://openalex.org/W127416991"],"abstract_inverted_index":{"We":[0],"introduce":[1],"FFTNet,":[2],"a":[3,26,33,60,71],"deep":[4,34],"learning":[5],"approach":[6,11],"synthesizing":[7],"audio":[8,29,54],"waveforms.":[9,55],"Our":[10],"builds":[12],"on":[13],"the":[14,62],"recent":[15],"WaveNet":[16],"project,":[17],"which":[18],"showed":[19],"that":[20],"it":[21,45],"was":[22],"possible":[23],"to":[24],"synthesize":[25],"natural":[27],"sounding":[28],"waveform":[30],"directly":[31],"from":[32],"convolutional":[35],"neural":[36],"network.":[37],"FFTNet":[38],"offers":[39],"two":[40],"improvements":[41],"over":[42],"WaveNet.":[43],"First":[44],"is":[46],"substantially":[47],"faster,":[48],"allowing":[49],"for":[50],"real-time":[51],"synthesis":[52],"of":[53],"Second,":[56],"when":[57],"used":[58],"as":[59,68],"vocoder,":[61],"resulting":[63],"speech":[64],"sounds":[65],"more":[66],"natural,":[67],"measured":[69],"via":[70],"\u201cmean":[72],"opinion":[73],"score\u201d":[74],"test.":[75]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}