{"id":"https://openalex.org/W4366308362","doi":"https://doi.org/10.1109/ictai56018.2022.00042","title":"MHTTS: Fast Multi-head Text-to-speech For Spontaneous Speech With Imperfect Transcription","display_name":"MHTTS: Fast Multi-head Text-to-speech For Spontaneous Speech With Imperfect Transcription","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4366308362","doi":"https://doi.org/10.1109/ictai56018.2022.00042"},"language":"en","primary_location":{"id":"doi:10.1109/ictai56018.2022.00042","doi":"https://doi.org/10.1109/ictai56018.2022.00042","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai56018.2022.00042","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.07438","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064203771","display_name":"Dabiao Ma","orcid":"https://orcid.org/0009-0006-0186-7476","observed_orcids":["https://orcid.org/0009-0006-0186-7476"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dabiao Ma","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070507407","display_name":"Zhiba Su","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiba Su","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614239","display_name":"Yitong Zhang","orcid":"https://orcid.org/0009-0007-2824-118X","observed_orcids":["https://orcid.org/0009-0007-2824-118X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yitong Zhang","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Emily Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emily Huang","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457556","display_name":"Meng Li","orcid":"https://orcid.org/0000-0003-2123-2444","observed_orcids":["https://orcid.org/0000-0003-2123-2444","https://orcid.org/0009-0001-4473-5450"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007489001","display_name":"Qiwen Lyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiwen Lyu","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398500","display_name":"Feng Ye","orcid":"https://orcid.org/0000-0003-0005-2073","observed_orcids":["https://orcid.org/0000-0003-0005-2073"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Ye","raw_affiliation_strings":["360 Digital Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 Digital Lab, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1725679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"239","last_page":"244"},"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":9.999999747378752e-05,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9340000152587891},{"id":"https://openalex.org/keywords/multi-speaker-speech-synthesis","display_name":"multi-speaker speech synthesis","score":0.8130000233650208},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.8069999814033508},{"id":"https://openalex.org/keywords/transcription-errors","display_name":"transcription errors","score":0.6990000009536743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7870000004768372},{"id":"https://openalex.org/keywords/inference-speed","display_name":"inference speed","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8650202751159668},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.8051590919494629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7242279052734375},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5429219603538513},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5052369236946106},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48858460783958435},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4469984471797943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44225090742111206},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41218143701553345},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40369242429733276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35684382915496826},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ictai56018.2022.00042","doi":"https://doi.org/10.1109/ictai56018.2022.00042","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai56018.2022.00042","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.07438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.07438","pdf_url":"https://arxiv.org/pdf/2201.07438","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2201.07438","doi":"https://doi.org/10.48550/arxiv.2201.07438","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2201.07438","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.07438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.07438","pdf_url":"https://arxiv.org/pdf/2201.07438","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366308362.pdf","grobid_xml":"https://content.openalex.org/works/W4366308362.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1731081199","https://openalex.org/W1901129140","https://openalex.org/W1981276685","https://openalex.org/W2519091744","https://openalex.org/W2626778328","https://openalex.org/W2749074593","https://openalex.org/W2766812927","https://openalex.org/W2767052532","https://openalex.org/W2785885194","https://openalex.org/W2788851830","https://openalex.org/W2809994596","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972817752","https://openalex.org/W2997481372","https://openalex.org/W3033411150","https://openalex.org/W3037932933","https://openalex.org/W3095173472","https://openalex.org/W3095990227","https://openalex.org/W3098403858","https://openalex.org/W3161109662","https://openalex.org/W3197478142","https://openalex.org/W3198533616","https://openalex.org/W6745697700","https://openalex.org/W6765987481","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W4390075359","https://openalex.org/W3095545636","https://openalex.org/W2903739847","https://openalex.org/W3215895588","https://openalex.org/W7162971678","https://openalex.org/W3198213150","https://openalex.org/W4402111774","https://openalex.org/W4372341816","https://openalex.org/W3198048682","https://openalex.org/W3024605872"],"abstract_inverted_index":{"Neural":[0],"network":[1],"based":[2],"end-to-end":[3],"Text-to-Speech":[4],"(TTS)":[5],"has":[6,76],"greatly":[7],"improved":[8],"the":[9],"quality":[10,84],"of":[11,18,49,96],"synthesized":[12],"speech.":[13],"However,":[14],"(the":[15],"efficient":[16],"usage":[17],"massive)[how":[19],"to":[20,46,71,101],"efficiently":[21],"use":[22],"massive]":[23],"spontaneous":[24],"speech":[25,51],"without":[26,73],"transcription":[27,47,70],"remains":[28],"an":[29,112],"open":[30],"problem.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,54],"propose":[36],"MHTTS,":[37],"a":[38,56,60],"fast":[39],"multi-speaker":[40,85],"TTS":[41],"system":[42,81,93],"that":[43,62],"is":[44,94],"robust":[45],"errors":[48],"real":[50],"data.":[52],"Specifically,":[53],"introduce":[55],"multi-head":[57],"model":[58],"and":[59],"method":[61],"transfer":[63],"text":[64,99],"information":[65,100],"from":[66],"corpora":[67,72],"with":[68,87,103],"manual":[69],"annotation.":[74],"MHTTS":[75],"two":[77],"advantages:":[78],"1)":[79],"Our":[80,92],"synthesizes":[82],"better":[83],"voice":[86],"faster":[88],"inference":[89],"speed.":[90],"2)":[91],"capable":[95],"transferring":[97],"correct":[98],"data":[102],"imperfect":[104],"transcription,":[105],"simulated":[106],"using":[107],"corruption,":[108],"or":[109],"provided":[110],"by":[111],"Automatic":[113],"Speech":[114],"Recognizer":[115],"(ASR).":[116]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-04-20T00:00:00"}