{"id":"https://openalex.org/W3174102645","doi":"https://doi.org/10.21437/interspeech.2021-189","title":"Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration","display_name":"Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3174102645","doi":"https://doi.org/10.21437/interspeech.2021-189","mag":"3174102645"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-189","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-189","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":"article","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/A5103999890","display_name":"Chuanxin Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuanxin Tang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005976848","display_name":"Chong Luo","orcid":"https://orcid.org/0000-0003-4654-5682"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Luo","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079531245","display_name":"Zhiyuan Zhao","orcid":"https://orcid.org/0000-0002-1227-5058"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004867590","display_name":"Dacheng Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dacheng Yin","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632793","display_name":"Yucheng Zhao","orcid":"https://orcid.org/0000-0002-9610-3025"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Zhao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049963367","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-2531-3137"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103999890"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72108548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3600","last_page":"3604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9923999905586243,"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":0.9843999743461609,"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/zero","display_name":"Zero (linguistics)","score":0.6976837515830994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6787294745445251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6291444301605225},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.610833466053009},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5230470895767212},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44893157482147217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3823096752166748},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23712745308876038}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6976837515830994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787294745445251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6291444301605225},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.610833466053009},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5230470895767212},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44893157482147217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3823096752166748},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23712745308876038},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-189","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-189","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":16,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2120847449","https://openalex.org/W2402356521","https://openalex.org/W2747874407","https://openalex.org/W2808706139","https://openalex.org/W2903739847","https://openalex.org/W2940703732","https://openalex.org/W2946200149","https://openalex.org/W2960274051","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015676952","https://openalex.org/W3033411150","https://openalex.org/W3034794073","https://openalex.org/W3160438760","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2366718574","https://openalex.org/W4388696151","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566","https://openalex.org/W2380471679"],"abstract_inverted_index":{"Given":[0],"a":[1,31,39,66,72,86,146,169,175],"piece":[2],"of":[3,59,75,101,141,156],"speech":[4,10,15,24,96,128,144],"and":[5,44,93,127],"its":[6],"transcript":[7],"text,":[8],"text-based":[9],"editing":[11,26],"aims":[12],"to":[13,49,79,90,108,122],"generate":[14,91,138],"that":[16,63,152],"can":[17],"be":[18],"seamlessly":[19],"inserted":[20,116],"into":[21],"the":[22,27,35,47,50,102,115,132,139,142,154,160],"given":[23],"by":[25,174],"transcript.Existing":[28],"methods":[29],"adopt":[30],"two-stage":[32],"approach:":[33],"synthesize":[34],"input":[36],"text":[37,125],"using":[38,53],"generic":[40],"text-to-speech":[41],"(TTS)":[42],"engine":[43,173],"then":[45],"transform":[46],"voice":[48,52,54],"desired":[51],"conversion":[55],"(VC).A":[56],"major":[57],"problem":[58,68],"this":[60,82],"framework":[61,89],"is":[62,65,120],"VC":[64],"challenging":[67],"which":[69],"usually":[70],"needs":[71],"moderate":[73],"amount":[74],"parallel":[76],"training":[77,99,157],"data":[78,100,158],"work":[80],"satisfactorily.In":[81],"paper,":[83],"we":[84,106,136],"propose":[85],"one-stage":[87],"context-aware":[88],"natural":[92],"coherent":[94],"target":[95,103],"without":[97],"any":[98],"speaker.In":[104],"particular,":[105],"manage":[107],"perform":[109],"accurate":[110],"zero-shot":[111,171],"duration":[112,119],"prediction":[113],"for":[114,159],"text.The":[117],"predicted":[118],"used":[121],"regulate":[123],"both":[124],"embedding":[126],"embedding.Then,":[129],"based":[130],"on":[131],"aligned":[133],"cross-modality":[134],"input,":[135],"directly":[137],"mel-spectrogram":[140],"edited":[143],"with":[145],"transformer-based":[147],"decoder.Subjective":[148],"listening":[149],"tests":[150],"show":[151],"despite":[153],"lack":[155],"speaker,":[161],"our":[162],"method":[163],"has":[164],"achieved":[165],"satisfactory":[166],"results.It":[167],"outperforms":[168],"recent":[170],"TTS":[172],"large":[176],"margin.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}