{"id":"https://openalex.org/W4283722828","doi":"https://doi.org/10.21437/interspeech.2022-245","title":"RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion","display_name":"RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283722828","doi":"https://doi.org/10.21437/interspeech.2022-245"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-245","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-245","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","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/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":true,"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/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":false,"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/A5100360935","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0003-0412-8805"},"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":"Yanqing Liu","raw_affiliation_strings":["Microsoft Azure Speech, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626793","display_name":"Xiaoqiang Wang","orcid":"https://orcid.org/0000-0001-6096-8011"},"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":"Xiaoqiang Wang","raw_affiliation_strings":["Microsoft Azure Speech, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569386","display_name":"Zhiyuan Zhao","orcid":"https://orcid.org/0000-0002-3597-226X"},"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/A5108730758","display_name":"Yucheng Zhao","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":"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":"middle","author":{"id":"https://openalex.org/A5008612863","display_name":"Zhiwei Xiong","orcid":"https://orcid.org/0000-0002-9787-7460"},"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":"Zhiwei Xiong","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/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"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":"Sheng Zhao","raw_affiliation_strings":["Microsoft Azure Speech, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100539988","display_name":"Chong Luo","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":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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5004867590"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5194,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61818574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1571","last_page":"1575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9970999956130981,"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/naturalness","display_name":"Naturalness","score":0.8139362931251526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8105757236480713},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8104240894317627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7139871716499329},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6299713850021362},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6064304113388062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.571241557598114},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5461883544921875},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5223166346549988},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4482106864452362},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4297918379306793},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4274940490722656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4191479980945587},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41373389959335327},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0769321620464325},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07106032967567444}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8139362931251526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105757236480713},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8104240894317627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7139871716499329},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6299713850021362},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6064304113388062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.571241557598114},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5461883544921875},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5223166346549988},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4482106864452362},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4297918379306793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4274940490722656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4191479980945587},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41373389959335327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0769321620464325},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07106032967567444},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-245","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-245","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","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":22,"referenced_works":["https://openalex.org/W2747874407","https://openalex.org/W2808706139","https://openalex.org/W2945478979","https://openalex.org/W2960274051","https://openalex.org/W2972659941","https://openalex.org/W2995435108","https://openalex.org/W3016181583","https://openalex.org/W3092028330","https://openalex.org/W3128910262","https://openalex.org/W3150572638","https://openalex.org/W3161109662","https://openalex.org/W3161627112","https://openalex.org/W3168527213","https://openalex.org/W3174102645","https://openalex.org/W3178839419","https://openalex.org/W3190965961","https://openalex.org/W3196001064","https://openalex.org/W3197580070","https://openalex.org/W3213227271","https://openalex.org/W4221160837","https://openalex.org/W4287239560","https://openalex.org/W4296068407"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,84,90],"new":[4],"\"decompose-and-edit\"":[5],"paradigm":[6],"for":[7],"the":[8,23,50,70,96,117],"text-based":[9],"speech":[10,16,31],"insertion":[11,17],"task":[12,93],"that":[13],"facilitates":[14],"arbitrarylength":[15],"and":[18,27,35,43,62,101,128],"even":[19],"full":[20],"sentence":[21],"generation.In":[22],"proposed":[24,47],"paradigm,":[25],"global":[26,51,74],"local":[28,97],"factors":[29,52],"in":[30,83,125],"are":[32,57],"explicitly":[33],"decomposed":[34],"separately":[36],"manipulated":[37],"to":[38,48,69,78,94],"achieve":[39,79,103,108],"high":[40,80,109],"speaker":[41,81],"similarity":[42,82],"continuous":[44],"prosody.Specifically,":[45],"we":[46,76,88],"represent":[49],"by":[53,59,66],"multiple":[54],"tokens,":[55],"which":[56],"extracted":[58],"cross-attention":[60],"operation":[61],"then":[63],"injected":[64],"back":[65],"link-attention":[67],"operation.Due":[68],"rich":[71],"representation":[72],"of":[73],"factors,":[75],"manage":[77],"zero-shot":[85],"manner.In":[86],"addition,":[87],"introduce":[89],"prosody":[91,98,105],"smoothing":[92],"make":[95],"factor":[99],"context-aware":[100],"therefore":[102],"satisfactory":[104],"continuity.We":[106],"further":[107],"voice":[110],"quality":[111],"with":[112],"an":[113],"adversarial":[114],"training":[115],"stage.In":[116],"subjective":[118],"test,":[119],"our":[120],"method":[121],"achieves":[122],"state-of-the-art":[123],"performance":[124],"both":[126],"naturalness":[127],"similarity.Audio":[129],"samples":[130],"can":[131],"be":[132],"found":[133],"at":[134],"https://ydcustc.github.io/retrieverTTS-demo/.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}