{"id":"https://openalex.org/W4395961568","doi":"https://doi.org/10.21437/blizzard.2021-4","title":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","display_name":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","publication_year":2021,"publication_date":"2021-10-23","ids":{"openalex":"https://openalex.org/W4395961568","doi":"https://doi.org/10.21437/blizzard.2021-4"},"language":"en","primary_location":{"id":"doi:10.21437/blizzard.2021-4","doi":"https://doi.org/10.21437/blizzard.2021-4","is_oa":false,"landing_page_url":"https://doi.org/10.21437/blizzard.2021-4","pdf_url":null,"source":{"id":"https://openalex.org/S7407089039","display_name":"The Blizzard Challenge","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Blizzard Challenge 2021","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.13673","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025094649","display_name":"Shilun Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shilun Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wenchao Su","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenchao Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457472","display_name":"Meng Li","orcid":"https://orcid.org/0000-0002-4725-7159","observed_orcids":["https://orcid.org/0000-0002-4725-7159"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692260","display_name":"Fenglong Xie","orcid":"https://orcid.org/0000-0002-1206-3696","observed_orcids":["https://orcid.org/0000-0002-1206-3696"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fenglong Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116159413","display_name":"Xinhui Li","orcid":"https://orcid.org/0009-0006-5522-0037","observed_orcids":["https://orcid.org/0009-0006-5522-0037"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Li Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Lu","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":0.094,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.36194983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"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":9.999999747378752e-05,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9399999976158142},{"id":"https://openalex.org/keywords/non-autoregressive-decoding","display_name":"non-autoregressive decoding","score":0.9190000295639038},{"id":"https://openalex.org/keywords/transformer-encoder","display_name":"Transformer encoder","score":0.6169999837875366},{"id":"https://openalex.org/keywords/dense-connections","display_name":"dense connections","score":0.7609999775886536},{"id":"https://openalex.org/keywords/mandarin-speech-synthesis","display_name":"Mandarin speech synthesis","score":0.7929999828338623},{"id":"https://openalex.org/keywords/exposure-bias","display_name":"exposure bias","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8605322241783142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6566762924194336},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.5357877612113953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4488787353038788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3862264156341553},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.24399247765541077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24206212162971497},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.23690325021743774},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.19255465269088745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10874068737030029}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/blizzard.2021-4","doi":"https://doi.org/10.21437/blizzard.2021-4","is_oa":false,"landing_page_url":"https://doi.org/10.21437/blizzard.2021-4","pdf_url":null,"source":{"id":"https://openalex.org/S7407089039","display_name":"The Blizzard Challenge","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Blizzard Challenge 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.13673","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.13673","pdf_url":"https://arxiv.org/pdf/2109.13673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2109.13673","doi":"https://doi.org/10.48550/arxiv.2109.13673","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.13673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.13673","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.13673","pdf_url":"https://arxiv.org/pdf/2109.13673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395961568.pdf","grobid_xml":"https://content.openalex.org/works/W4395961568.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1810943226","https://openalex.org/W1849277567","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1910657905","https://openalex.org/W2130942839","https://openalex.org/W2194775991","https://openalex.org/W2210838531","https://openalex.org/W2434741482","https://openalex.org/W2560512785","https://openalex.org/W2766812927","https://openalex.org/W2794490148","https://openalex.org/W2886769154","https://openalex.org/W2896060389","https://openalex.org/W2898322826","https://openalex.org/W2901997113","https://openalex.org/W2907222274","https://openalex.org/W2941814890","https://openalex.org/W2948947170","https://openalex.org/W2963248296","https://openalex.org/W2963446712","https://openalex.org/W2963609956","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2971905065","https://openalex.org/W2972951102","https://openalex.org/W2981857663","https://openalex.org/W2982174878"],"related_works":["https://openalex.org/W3196964833","https://openalex.org/W4385571513","https://openalex.org/W3091928890","https://openalex.org/W3197294703","https://openalex.org/W4212772209","https://openalex.org/W4411120407","https://openalex.org/W4417086913","https://openalex.org/W3197858274","https://openalex.org/W4387064179","https://openalex.org/W3198213150"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Nana-HDR,":[3],"a":[4,26,42,51,57],"new":[5],"non-attentive":[6],"non-autoregressive":[7,53],"model":[8,64],"with":[9,30],"hybrid":[10,69],"Transformer-based":[11,93],"Dense-fuse":[12,28],"encoder":[13,29,70],"and":[14,41,71,103,107,124],"RNN-based":[15,54],"decoder":[16],"for":[17,37,46],"TTS.":[18],"It":[19],"mainly":[20],"consists":[21],"of":[22,61,83,92],"three":[23],"parts:":[24],"Firstly,":[25],"novel":[27],"dense":[31],"connections":[32],"between":[33],"basic":[34],"Transformer":[35],"blocks":[36],"coarse":[38],"feature":[39,48],"fusion":[40],"multi-head":[43],"attention":[44,63],"layer":[45],"fine":[47],"fusion.":[49],"Secondly,":[50],"single-layer":[52],"decoder.":[55,72],"Thirdly,":[56],"duration":[58,112],"predictor":[59],"instead":[60],"an":[62],"that":[65,75],"connects":[66],"the":[67,81],"above":[68],"Experiments":[73],"indicate":[74],"Nana-HDR":[76,118],"gives":[77],"full":[78],"play":[79],"to":[80,115],"advantages":[82],"each":[84],"component,":[85],"such":[86],"as":[87],"strong":[88],"text":[89],"encoding":[90],"ability":[91],"encoder,":[94],"stateful":[95],"decoding":[96],"without":[97],"being":[98],"bothered":[99],"by":[100,111],"exposure":[101],"bias":[102],"local":[104],"information":[105],"preference,":[106],"stable":[108],"alignment":[109],"provided":[110],"predictor.":[113],"Due":[114],"these":[116],"advantages,":[117],"achieves":[119],"competitive":[120],"performance":[121],"in":[122],"naturalness":[123],"robustness":[125],"on":[126],"two":[127],"Mandarin":[128],"corpora.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-04-29T00:00:00"}