{"id":"https://openalex.org/W3198769980","doi":"https://doi.org/10.21437/interspeech.2021-1897","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","display_name":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198769980","doi":"https://doi.org/10.21437/interspeech.2021-1897","mag":"3198769980"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1897","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5071702566","display_name":"Nanxin Chen","orcid":"https://orcid.org/0000-0001-6698-1604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanxin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103947107","display_name":"Mohammad Norouzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Norouzi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102811560","display_name":"William Chan","orcid":"https://orcid.org/0000-0001-6205-255X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Chan","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":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3765","last_page":"3769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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":0.7854622602462769},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.633567214012146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.58841872215271},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5680966377258301},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5258572697639465},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.49697497487068176},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47266635298728943},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.45532137155532837},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39428454637527466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36049431562423706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10840499401092529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854622602462769},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.633567214012146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.58841872215271},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5680966377258301},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5258572697639465},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.49697497487068176},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47266635298728943},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.45532137155532837},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39428454637527466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36049431562423706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10840499401092529},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1897","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3128296386","https://openalex.org/W4387636010","https://openalex.org/W2491221267","https://openalex.org/W2034475059","https://openalex.org/W3206651063","https://openalex.org/W3198095025","https://openalex.org/W3118479201","https://openalex.org/W4229728092","https://openalex.org/W4396908826","https://openalex.org/W2379090666"],"abstract_inverted_index":{"This":[0,49],"paper":[1],"introduces":[2],"WaveGrad":[3,12,54,89],"2,":[4],"a":[5,29,63,76,92,124],"non-autoregressive":[6],"generative":[7],"model":[8,33,114,137],"for":[9],"text-to-speech":[10],"synthesis.":[11],"2":[13,90],"is":[14],"trained":[15],"to":[16,51,95],"estimate":[17],"the":[18,21,26,52,86,105,113,121],"gradient":[19],"of":[20,25,78,107,123],"log":[22],"conditional":[23],"density":[24],"waveform":[27],"given":[28],"phoneme":[30,37],"sequence.":[31,88],"The":[32,66],"takes":[34],"an":[35,41,46],"input":[36],"sequence,":[38],"and":[39,74,100],"through":[40,75,103],"iterative":[42,67],"refinement":[43,68,79,108],"process,":[44],"generates":[45],"audio":[47,87],"waveform.":[48],"contrasts":[50],"original":[53],"vocoder":[55],"which":[56],"conditions":[57],"on":[58],"mel-spectrogram":[59],"features,":[60],"generated":[61],"by":[62],"separate":[64],"model.":[65],"process":[69],"starts":[70],"from":[71],"Gaussian":[72],"noise,":[73],"series":[77],"steps":[80],"(e.g.,":[81],"50":[82],"steps),":[83],"progressively":[84],"recovers":[85],"offers":[91],"natural":[93],"way":[94],"trade-off":[96],"between":[97],"inference":[98],"speed":[99],"sample":[101],"quality,":[102],"adjusting":[104],"number":[106],"steps.":[109],"Experiments":[110],"show":[111],"that":[112],"can":[115],"generate":[116],"high":[117],"fidelity":[118],"audio,":[119],"approaching":[120],"performance":[122],"state-of-the-art":[125],"neural":[126],"TTS":[127],"system.":[128],"We":[129],"also":[130],"report":[131],"various":[132],"ablation":[133],"studies":[134],"over":[135],"different":[136],"configurations.":[138],"Audio":[139],"samples":[140],"are":[141],"available":[142],"at":[143],"this":[144],"https":[145],"URL.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}