{"id":"https://openalex.org/W3095389792","doi":"https://doi.org/10.21437/interspeech.2020-2464","title":"High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency","display_name":"High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095389792","doi":"https://doi.org/10.21437/interspeech.2020-2464","mag":"3095389792"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2464","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.09052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310876","display_name":"Georgios Vamvoukakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Vamvoukakis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050072052","display_name":"\u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c2 \u039c\u03b1\u03c1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Markopoulos","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108894078","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037667852","display_name":"Georgia Maniati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgia Maniati","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067728489","display_name":"Panos Kakoulidis","orcid":"https://orcid.org/0000-0003-2980-2528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panos Kakoulidis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111393130","display_name":"Spyros Raptis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyros Raptis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006509336","display_name":"Hyoung-Min Park","orcid":"https://orcid.org/0000-0001-7397-8286"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyoungmin Park","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["[Samsung]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Samsung]","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8436,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92593879,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2022","last_page":"2026"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.8202836513519287},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6376030445098877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6023103594779968},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4834488332271576},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4628656804561615},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.45752912759780884},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4565422832965851},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45554959774017334},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4294987916946411},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4255063831806183},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3515051603317261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23159590363502502},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09113901853561401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202836513519287},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6376030445098877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6023103594779968},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4834488332271576},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4628656804561615},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.45752912759780884},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4565422832965851},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45554959774017334},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4294987916946411},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4255063831806183},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3515051603317261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23159590363502502},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09113901853561401},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2464","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.09052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09052","pdf_url":"https://arxiv.org/pdf/2111.09052","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.09052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09052","pdf_url":"https://arxiv.org/pdf/2111.09052","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1810943226","https://openalex.org/W2095705004","https://openalex.org/W2519091744","https://openalex.org/W2767052532","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2948211236","https://openalex.org/W2949382160","https://openalex.org/W2962970071","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2970730223","https://openalex.org/W2970971581","https://openalex.org/W2996286887","https://openalex.org/W3015338123","https://openalex.org/W3015922793","https://openalex.org/W3016160783","https://openalex.org/W3038172701","https://openalex.org/W3095459301","https://openalex.org/W4293714597","https://openalex.org/W4294619240","https://openalex.org/W4295312788","https://openalex.org/W4298580827","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,22],"end-to-end":[4,146],"text-to-speech":[5],"system":[6,18,147],"with":[7,111],"low":[8],"latency":[9,92,113],"on":[10,120,127,141],"a":[11,58,84,89,121,128],"CPU,":[12,130],"suitable":[13,65],"for":[14,32,66,88,138],"real-time":[15,119,139],"applications.":[16],"The":[17,144],"is":[19,50,54,75,81,94,155],"composed":[20],"of":[21],"autoregressive":[23],"attention-based":[24],"sequence-to-sequence":[25],"acoustic":[26,36,78,105],"model":[27,37,106],"and":[28,47,77,124],"the":[29,44,73,97,104,135],"LPCNet":[30],"vocoder":[31],"waveform":[33],"generation.":[34,70],"An":[35],"architecture":[38],"that":[39,103],"adopts":[40],"modules":[41],"from":[42,96],"both":[43,142],"Tacotron":[45],"1":[46],"2":[48],"models":[49],"proposed,":[51],"while":[52],"stability":[53],"ensured":[55],"by":[56,157],"using":[57],"recently":[59],"proposed":[60],"purely":[61],"location-based":[62],"attention":[63],"mechanism,":[64],"arbitrary":[67],"sentence":[68,98],"length":[69],"During":[71],"inference,":[72],"decoder":[74],"unrolled":[76],"feature":[79,109],"generation":[80],"performed":[82],"in":[83],"streaming":[85],"manner,":[86],"allowing":[87],"nearly":[90],"constant":[91],"which":[93,154],"independent":[95],"length.":[99],"Experimental":[100],"results":[101],"show":[102],"can":[107,148],"produce":[108],"sequences":[110],"minimal":[112],"about":[114],"31":[115],"times":[116,126],"faster":[117],"than":[118],"computer":[122],"CPU":[123],"6.5":[125],"mobile":[129],"enabling":[131],"it":[132],"to":[133],"meet":[134],"conditions":[136],"required":[137],"applications":[140],"devices.":[143],"full":[145],"generate":[149],"almost":[150],"natural":[151],"quality":[152],"speech,":[153],"verified":[156],"listening":[158],"tests.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
