{"id":"https://openalex.org/W2954386831","doi":"https://doi.org/10.21437/interspeech.2019-1424","title":"Towards Achieving Robust Universal Neural Vocoding","display_name":"Towards Achieving Robust Universal Neural Vocoding","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2954386831","doi":"https://doi.org/10.21437/interspeech.2019-1424","mag":"2954386831"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1424","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046126186","display_name":"Bartosz Putrycz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bartosz Putrycz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021819126","display_name":"Vatsal Aggarwal","orcid":"https://orcid.org/0000-0002-6477-1264"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vatsal Aggarwal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"185"},"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/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/T11447","display_name":"Blind Source Separation Techniques","score":0.9986000061035156,"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":0.755212664604187},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6412124037742615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6402603387832642},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42219728231430054},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42216286063194275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37647807598114014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36335232853889465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755212664604187},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6412124037742615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6402603387832642},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42219728231430054},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42216286063194275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37647807598114014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36335232853889465},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1424","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W30609886","https://openalex.org/W169745891","https://openalex.org/W1544516254","https://openalex.org/W1997402792","https://openalex.org/W2066999516","https://openalex.org/W2120634960","https://openalex.org/W2120847449","https://openalex.org/W2191779130","https://openalex.org/W2395578248","https://openalex.org/W2400063444","https://openalex.org/W2401318443","https://openalex.org/W2409959948","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2572097499","https://openalex.org/W2757519008","https://openalex.org/W2762101354","https://openalex.org/W2786868129","https://openalex.org/W2808706139","https://openalex.org/W2888169323","https://openalex.org/W2889064624","https://openalex.org/W2889092828","https://openalex.org/W2889329491","https://openalex.org/W2890983311","https://openalex.org/W2916985722","https://openalex.org/W2963300588","https://openalex.org/W2963411216","https://openalex.org/W2963522141","https://openalex.org/W2963654953","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W4294619240","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,45,63,68,83],"potential":[4],"universality":[5],"of":[6,26,29,43,98,109],"neural":[7],"vocoders.We":[8],"train":[9],"a":[10,50,93],"WaveRNN-based":[11],"vocoder":[12,20,84],"on":[13],"74":[14],"speakers":[15],"coming":[16],"from":[17,49,58],"17":[18],"languages.This":[19],"is":[21],"shown":[22,102],"to":[23,39,103],"be":[24,104],"capable":[25],"generating":[27],"speech":[28],"consistently":[30],"good":[31],"quality":[32],"(98%":[33],"relative":[34,96],"mean":[35],"MUSHRA":[36,97],"when":[37,62,76],"compared":[38],"natural":[40],"speech)":[41],"regardless":[42,108],"whether":[44],"input":[46],"spectrogram":[47],"comes":[48],"speaker":[51],"or":[52,57,75,81,116,118],"style":[53],"seen":[54,112],"during":[55,113],"training":[56,114],"an":[59],"out-of-domain":[60],"scenario":[61],"recording":[64],"conditions":[65],"are":[66,101],"studio-quality.When":[67],"recordings":[69],"show":[70],"significant":[71],"changes":[72],"in":[73],"quality,":[74],"moving":[77],"towards":[78],"non-speech":[79],"vocalizations":[80],"singing,":[82],"still":[85],"significantly":[86],"outperforms":[87],"speaker-dependent":[88],"vocoders,":[89],"but":[90],"operates":[91],"at":[92],"lower":[94],"average":[95],"75%.These":[99],"results":[100],"consistent":[105],"across":[106],"languages,":[107],"them":[110],"being":[111],"(e.g.English":[115],"Japanese)":[117],"unseen":[119],"(e.g.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}