{"id":"https://openalex.org/W3160353145","doi":"https://doi.org/10.1109/icassp39728.2021.9413658","title":"Patnet : A Phoneme-Level Autoregressive Transformer Network for Speech Synthesis","display_name":"Patnet : A Phoneme-Level Autoregressive Transformer Network for Speech Synthesis","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160353145","doi":"https://doi.org/10.1109/icassp39728.2021.9413658","mag":"3160353145"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413658","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":"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/A5100769192","display_name":"Shiming Wang","orcid":"https://orcid.org/0000-0003-3222-3914"},"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Wang","raw_affiliation_strings":["University of Science and Technology of China,NELSLIP,Hefei,China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","NELSLIP, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"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":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China,NELSLIP,Hefei,China","NELSLIP, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5684","last_page":"5688"},"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":0.9955000281333923,"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":0.9941999912261963,"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":0.7894856929779053},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7665872573852539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6952763795852661},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.692389965057373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6870001554489136},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6714566946029663},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.549380898475647},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.497165709733963},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4722920060157776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44574981927871704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.391616553068161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3434649705886841},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15853825211524963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13933414220809937},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11835625767707825},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06037673354148865}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7894856929779053},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7665872573852539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6952763795852661},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.692389965057373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6870001554489136},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6714566946029663},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.549380898475647},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.497165709733963},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4722920060157776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44574981927871704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.391616553068161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3434649705886841},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15853825211524963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13933414220809937},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11835625767707825},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06037673354148865},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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:10.1109/icassp39728.2021.9413658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413658","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2120847449","https://openalex.org/W2133564696","https://openalex.org/W2154920538","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W3016136182","https://openalex.org/W3016160783","https://openalex.org/W3033411150","https://openalex.org/W3130016944","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6640212811","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6780226713","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2110108310","https://openalex.org/W1544516254","https://openalex.org/W2579204149","https://openalex.org/W2174199565","https://openalex.org/W2181773877","https://openalex.org/W2904846757","https://openalex.org/W2968379855","https://openalex.org/W1481612584","https://openalex.org/W1564152904","https://openalex.org/W2154644810"],"abstract_inverted_index":{"Aiming":[0],"at":[1],"efficiently":[2],"predicting":[3],"acoustic":[4,17,93],"features":[5],"with":[6,82],"high":[7],"naturalness":[8,141],"and":[9,31,88,119,138],"robustness,":[10],"this":[11],"paper":[12],"proposes":[13],"PATNet,":[14],"a":[15,40,124],"neural":[16],"model":[18,42],"for":[19,47],"speech":[20,106,125],"synthesis":[21],"using":[22],"phoneme-level":[23,70],"autoregression.":[24],"PATNet":[25,38,53,73,109,129],"accepts":[26],"phoneme":[27,59,98],"sequences":[28],"as":[29,86],"input":[30],"is":[32],"built":[33],"based":[34],"on":[35],"Transformer":[36],"structure.":[37],"adopts":[39],"duration":[41],"instead":[43],"of":[44,52,66,92],"attention":[45],"mechanism":[46],"sequence":[48],"alignment.":[49],"The":[50],"decoder":[51],"predicts":[54],"multi-frame":[55],"spectra":[56,65],"within":[57],"one":[58],"in":[60],"parallel":[61],"given":[62],"the":[63,80,90,105],"predicted":[64],"previous":[67],"phonemes.":[68],"Such":[69],"autoregression":[71],"enables":[72],"to":[74],"achieve":[75],"higher":[76],"inference":[77,134],"efficiency":[78],"than":[79,116,136,142],"models":[81],"frame-level":[83],"autoregression,":[84],"such":[85],"Transformer-TTS,":[87],"improves":[89],"robustness":[91],"feature":[94],"prediction":[95],"by":[96,108,123],"utilizing":[97],"boundaries":[99],"explicitly.":[100],"Experimental":[101],"results":[102],"show":[103],"that":[104],"synthesized":[107],"obtained":[110],"lower":[111],"character":[112],"error":[113],"rate":[114],"(CER)":[115],"Tacotron,":[117],"Transfomer-TTS":[118],"FastSpeech":[120],"when":[121],"evaluated":[122],"recognition":[126],"engine.":[127],"Besides,":[128],"achieved":[130],"10":[131],"times":[132],"faster":[133],"speed":[135],"Transformer-TTS":[137],"significantly":[139],"better":[140],"FastSpeech.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}