{"id":"https://openalex.org/W3162771752","doi":"https://doi.org/10.1109/icassp39728.2021.9413969","title":"A New High Quality Trajectory Tiling Based Hybrid TTS In Real Time","display_name":"A New High Quality Trajectory Tiling Based Hybrid TTS In Real Time","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162771752","doi":"https://doi.org/10.1109/icassp39728.2021.9413969","mag":"3162771752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101692260","display_name":"Fenglong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng-Long Xie","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701662","display_name":"Xinhui Li","orcid":"https://orcid.org/0000-0002-8398-8741"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin-Hui Li","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041866046","display_name":"Wenchao Su","orcid":"https://orcid.org/0000-0002-9851-9753"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-Chao Su","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"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":"Frank K. Soong","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":5,"corresponding_author_ids":["https://openalex.org/A5101692260"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52212697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5704","last_page":"5708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7174075841903687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.66477370262146},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6586092114448547},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5831553936004639},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5076323747634888},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4467221796512604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4301588237285614},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42785561084747314},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4182121157646179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3223353624343872},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07506135106086731},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0749477744102478}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7174075841903687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66477370262146},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6586092114448547},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5831553936004639},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5076323747634888},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4467221796512604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4301588237285614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42785561084747314},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4182121157646179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3223353624343872},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07506135106086731},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0749477744102478},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1576227399","https://openalex.org/W1600722501","https://openalex.org/W1992287499","https://openalex.org/W2024093103","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2294797155","https://openalex.org/W2394761397","https://openalex.org/W2406990556","https://openalex.org/W2519091744","https://openalex.org/W2674088828","https://openalex.org/W2903739847","https://openalex.org/W2949382160","https://openalex.org/W2963091184","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2964045208","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2973217961","https://openalex.org/W3015338123","https://openalex.org/W3015607139","https://openalex.org/W3016137096","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6675380101","https://openalex.org/W6696843773","https://openalex.org/W6711946264","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W7075637324"],"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/W2998781440","https://openalex.org/W2039489009"],"abstract_inverted_index":{"A":[0,16],"trajectory":[1,73],"tiling":[2],"based,":[3],"hybrid":[4,105,111],"TTS":[5,113,121],"is":[6,39,56,78],"revisited":[7],"in":[8,88],"this":[9],"study":[10],"for":[11,91],"improving":[12],"its":[13],"synthesis":[14],"performance.":[15],"combination":[17],"of":[18,64,68,85],"Transformer":[19],"encoder":[20],"and":[21,31,45,66,74,117,127],"RNN":[22],"based":[23],"decoder":[24],"architecture":[25],"where":[26],"two-level,":[27],"at":[28],"both":[29],"word":[30],"Chinese":[32],"phonetic":[33],"alphabet":[34],"letter":[35],"levels,":[36],"linguistic":[37],"representation":[38],"exploited":[40],"to":[41,80],"generate":[42],"a":[43,52],"cogent":[44],"smooth":[46],"speech":[47,95],"parameter":[48],"trajectory.":[49],"And":[50],"then":[51],"segment":[53],"candidate":[54],"lattice":[55,90],"constructed":[57,123],"by":[58],"minimizing":[59],"the":[60,71,82,89,93,103,118],"log":[61],"spectral":[62],"distortion":[63],"mel-spectrograms":[65],"RMSE":[67],"F0":[69],"between":[70],"generated":[72],"candidates.":[75],"Normalized":[76],"cross-correlation":[77],"used":[79],"find":[81],"best":[83],"sequence":[84],"\"wave-form":[86],"tiles\"":[87],"synthesizing":[92],"final":[94],"waveforms.":[96],"Subjective":[97],"A/B":[98],"preference":[99],"tests":[100],"show":[101],"that":[102],"new":[104],"system":[106,122],"outperforms":[107],"our":[108],"earlier":[109],"trajectory-tiling":[110],"baseline":[112],"(67%":[114],"vs":[115,130],"11%)":[116],"state-of-the-art,":[119],"real-time":[120],"with":[124],"Tacotron":[125],"2":[126],"LPC-Net":[128],"(56%":[129],"27%).":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}