{"id":"https://openalex.org/W3135619128","doi":null,"title":"Multilingual Byte2Speech Text-To-Speech Models Are Few-shot Spoken Language Learners","display_name":"Multilingual Byte2Speech Text-To-Speech Models Are Few-shot Spoken Language Learners","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3135619128","mag":"3135619128"},"language":"en","primary_location":{"id":"mag:3135619128","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2103.03541v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2103.03541v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103220846","display_name":"Mutian He","orcid":"https://orcid.org/0000-0002-8939-4207","observed_orcids":["https://orcid.org/0000-0002-8939-4207","https://orcid.org/0009-0004-1947-1061"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mutian He","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8939-4207","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684375","display_name":"Jingzhou Yang","orcid":"https://orcid.org/0000-0002-5092-6739","observed_orcids":["https://orcid.org/0000-0002-5092-6739"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingzhou Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5092-6739","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305","observed_orcids":["https://orcid.org/0000-0003-3028-6305"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3028-6305","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multilingual-text-to-speech","display_name":"multilingual text-to-speech","score":0.9190000295639038},{"id":"https://openalex.org/keywords/end-to-end-speech-synthesis","display_name":"end-to-end speech synthesis","score":0.8009999990463257},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9729999899864197},{"id":"https://openalex.org/keywords/spectrogram-generation","display_name":"spectrogram generation","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376306295394897},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7175617218017578},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.63310706615448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5251471996307373},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.505648136138916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4826122224330902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4205782115459442},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41039878129959106},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3135619128","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2103.03541v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3135619128","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2103.03541v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2144994235","https://openalex.org/W2494654097","https://openalex.org/W2519091744","https://openalex.org/W2550821151","https://openalex.org/W2903739847","https://openalex.org/W2945078028","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2973034126","https://openalex.org/W2981978471","https://openalex.org/W2987270981","https://openalex.org/W3027127570","https://openalex.org/W3046670326","https://openalex.org/W3048217770","https://openalex.org/W3080155331","https://openalex.org/W3081416955","https://openalex.org/W3096242366","https://openalex.org/W3097674564","https://openalex.org/W3113217815"],"related_works":["https://openalex.org/W3181257032","https://openalex.org/W4385764360","https://openalex.org/W4391640577","https://openalex.org/W7169816532","https://openalex.org/W4392903365","https://openalex.org/W2973034126","https://openalex.org/W4377866201","https://openalex.org/W4392114301","https://openalex.org/W4206596421","https://openalex.org/W4323207642"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,95,103],"multilingual":[3,110],"end-to-end":[4],"Text-To-Speech":[5],"framework":[6,25,79],"that":[7],"maps":[8],"byte":[9],"inputs":[10],"to":[11,28,30,73,90,98],"spectrograms,":[12],"thus":[13],"allowing":[14],"arbitrary":[15],"input":[16],"scripts.":[17],"Besides":[18],"strong":[19],"results":[20],"on":[21],"40+":[22],"languages,":[23],"the":[24,47,75,78,84,107],"demonstrates":[26],"capabilities":[27],"adapt":[29],"various":[31,87],"new":[32],"languages":[33],"under":[34],"extreme":[35],"low-resource":[36,81],"and":[37,63,83],"even":[38],"few-shot":[39],"scenarios":[40],"of":[41,49,77,86,106,109],"merely":[42],"40s":[43],"transcribed":[44],"recording":[45],"without":[46],"need":[48],"lexicon,":[50],"extra":[51],"corpus,":[52],"auxiliary":[53],"models,":[54],"or":[55],"particular":[56],"linguistic":[57],"expertise,":[58],"while":[59],"retains":[60],"satisfactory":[61],"intelligibility":[62],"naturalness":[64],"matching":[65],"rich-resource":[66],"models.":[67,111],"Exhaustive":[68],"comparative":[69],"studies":[70],"are":[71],"performed":[72],"reveal":[74],"potential":[76],"for":[80,102],"application":[82],"impact":[85],"factors":[88],"contributory":[89],"adaptation.":[91],"Furthermore,":[92],"we":[93],"propose":[94],"novel":[96],"method":[97],"extract":[99],"language-specific":[100],"sub-networks":[101],"better":[104],"understanding":[105],"mechanism":[108]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2021-03-15T00:00:00"}