{"id":"https://openalex.org/W4414394711","doi":"https://doi.org/10.3724/2096-7004.di.2025.0128","title":"Efficient and Natural Tibetan Speech Synthesis via Gaussian Noise-Improved Monotonic Alignment Search and Lightweight iSTFT Multiband Decoder","display_name":"Efficient and Natural Tibetan Speech Synthesis via Gaussian Noise-Improved Monotonic Alignment Search and Lightweight iSTFT Multiband Decoder","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414394711","doi":"https://doi.org/10.3724/2096-7004.di.2025.0128"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0128","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0128","pdf_url":"https://www.sciengine.com/doi/pdf/D27462F4F53C4A688056D79B48D672D7","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/D27462F4F53C4A688056D79B48D672D7","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042169051","display_name":"Shiqi Wu","orcid":"https://orcid.org/0000-0001-8010-2573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqi Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037049534","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0003-0342-2797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672021","display_name":"Jing Yu","orcid":"https://orcid.org/0000-0002-3966-511X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045844800","display_name":"Xiaona Xu","orcid":"https://orcid.org/0000-0001-8715-1618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaona Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0.12815722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250128","last_page":"20250128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9796000123023987,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9325000047683716,"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/inference","display_name":"Inference","score":0.5442000031471252},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5320000052452087},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44290000200271606},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4375999867916107},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4246000051498413},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.375900000333786},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3684999942779541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35499998927116394},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4503999948501587},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0128","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0128","pdf_url":"https://www.sciengine.com/doi/pdf/D27462F4F53C4A688056D79B48D672D7","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0128","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0128","pdf_url":"https://www.sciengine.com/doi/pdf/D27462F4F53C4A688056D79B48D672D7","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414394711.pdf","grobid_xml":"https://content.openalex.org/works/W4414394711.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"end-to-end":[1],"speech":[2,13,152],"synthesis":[3,14,24],"technology":[4],"has":[5],"made":[6,138],"significant":[7,148,173],"progress":[8],"in":[9,90,150,175],"general":[10],"domains,":[11],"Tibetan":[12,78,98,131],"still":[15],"faces":[16],"issues":[17],"such":[18],"as":[19,103],"inaccurate":[20],"alignment":[21,60],"and":[22,31,63,86,115,135,142,154,164,168,177],"unnatural":[23],"due":[25],"to":[26,70,93],"its":[27],"unique":[28,113],"linguistic":[29],"features":[30],"low-resource":[32],"data":[33],"sparsity.":[34],"To":[35,118],"address":[36],"these":[37],"challenges,":[38],"this":[39],"paper":[40],"proposes":[41],"the":[42,73,82,91,120,123,140,190,193],"EnhancedTTS":[43],"model,":[44,125],"which":[45],"incorporates":[46],"a":[47,56,64,107,130],"random":[48],"duration":[49],"predictor":[50],"based":[51],"on":[52],"generative":[53],"adversarial":[54],"networks,":[55],"Gaussian":[57],"noise-enhanced":[58],"monotonic":[59],"search":[61],"algorithm,":[62],"Transformer":[65],"block":[66],"with":[67,139,179],"residual":[68],"connections":[69],"significantly":[71],"improve":[72],"modeling":[74,104],"accuracy":[75],"of":[76,111,122,192],"complex":[77],"syllable":[79],"boundaries.":[80],"Additionally,":[81],"model":[83],"uses":[84],"iSTFT":[85],"multi-band":[87],"parallel":[88],"strategies":[89],"decoder":[92],"enhance":[94],"inference":[95,180],"speed.":[96],"Furthermore,":[97],"character":[99],"components":[100],"are":[101],"used":[102],"units,":[105],"providing":[106],"more":[108],"accurate":[109],"representation":[110],"Tibetan\u2019s":[112],"phonetic":[114],"structural":[116],"features.":[117],"validate":[119],"effectiveness":[121,191],"proposed":[124],"experiments":[126,187],"were":[127,137],"conducted":[128],"using":[129],"Amdo":[132],"dialect":[133],"dataset,":[134],"comparisons":[136],"VITS":[141,167],"FastSpeech2":[143],"models.":[144],"The":[145,156],"results":[146],"show":[147],"breakthroughs":[149],"both":[151],"quality":[153],"efficiency.":[155],"MOS":[157],"score":[158],"reached":[159],"4.69,":[160],"improving":[161],"by":[162,183],"3.1%":[163],"1.5%":[165],"over":[166],"FastSpeech2.":[169],"Objective":[170],"tests":[171],"showed":[172],"optimizations":[174],"RMSE":[176],"MCD,":[178],"speed":[181],"increasing":[182],"2-5":[184],"times.":[185],"Ablation":[186],"further":[188],"confirmed":[189],"key":[194],"modules.":[195]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}