{"id":"https://openalex.org/W7225833089","doi":"https://doi.org/10.20944/preprints202611.0988.v1","title":"Character Embedding Priors and Script Structure in Low-Resource Bangla Text-to-Speech Adaptation","display_name":"Character Embedding Priors and Script Structure in Low-Resource Bangla Text-to-Speech Adaptation","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225833089","doi":"https://doi.org/10.20944/preprints202611.0988.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0988.v1","doi":"https://doi.org/10.20944/preprints202611.0988.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0988.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0988.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057237080","display_name":"Wahid Sadique Koly","orcid":"https://orcid.org/0000-0001-8869-9183","observed_orcids":["https://orcid.org/0000-0001-8869-9183"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wahid Sadique Koly","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8869-9183","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5157894988","display_name":"Homaira Adiba","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Homaira Adiba","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5285-9448","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5057237080"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"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"}},{"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.7946000099182129},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6704000234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6074000000953674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871000289916992},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.572700023651123},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.382999986410141},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0988.v1","doi":"https://doi.org/10.20944/preprints202611.0988.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0988.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0988.v1","doi":"https://doi.org/10.20944/preprints202611.0988.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0988.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Character-level":[0],"text-to-speech":[1],"(TTS)":[2],"models":[3],"pretrained":[4,76,128],"on":[5,36,62,147],"Latin-script":[6],"data":[7],"are":[8],"usually":[9],"adapted":[10],"to":[11,19,87,96,195],"a":[12,48,108,136,148,204],"new":[13,167],"language":[14],"by":[15,81,102,124],"adding":[16],"its":[17],"characters":[18,46],"the":[20,93,97,144,158,166,169,176,187,190,199],"vocabulary.":[21],"We":[22],"ask":[23],"why":[24],"this":[25,131],"works":[26],"poorly":[27],"for":[28,41],"Bangla,":[29],"an":[30,56,179],"abugida,":[31],"when":[32],"F5-TTS":[33],"is":[34],"fine-tuned":[35],"one":[37],"hour":[38],"of":[39,53,111,151,165],"speech":[40],"3,000":[42],"updates:":[43],"native":[44],"Bengali":[45,112],"give":[47],"character":[49],"error":[50],"rate":[51],"(CER)":[52],"67.96%,":[54],"under":[55,203],"ASR":[57],"model":[58],"that":[59],"scores":[60],"1.93%":[61],"real":[63],"recordings.":[64],"Controlled":[65],"input":[66],"representations":[67,193],"separate":[68],"two":[69,191],"factors.":[70],"On":[71],"identical":[72],"phonemic":[73],"Latin":[74,192],"text,":[75],"embedding":[77],"rows":[78,95,129],"lower":[79],"CER":[80,123],"22.04":[82],"percentage":[83],"points":[84],"(pp)":[85],"relative":[86],"freshly":[88],"initialized":[89],"rows,":[90,107],"while":[91],"assigning":[92],"same":[94],"wrong":[98],"sounds":[99],"raises":[100],"it":[101],"51.53":[103],"pp.":[104],"With":[105],"fresh":[106],"lossless":[109],"re-encoding":[110],"text":[113],"(explicit":[114],"inherent":[115],"vowel,":[116],"merged":[117],"vowel":[118],"forms,":[119],"split":[120],"aspirates)":[121],"lowers":[122],"47.56":[125],"pp,":[126,197],"and":[127],"help":[130],"restructured":[132],"encoding":[133],"less":[134],"than":[135],"standard":[137],"transliteration.":[138],"All":[139],"five":[140,183],"tests":[141],"specified":[142],"before":[143],"runs":[145],"replicate":[146],"second":[149],"corpus":[150],"another":[152],"Bangla":[153],"variety,":[154],"and,":[155],"where":[156],"tested,":[157],"directions":[159],"hold":[160],"across":[161],"three":[162],"random":[163],"draws":[164],"embeddings;":[168],"effect":[170],"sizes,":[171],"however,":[172],"vary":[173],"strongly":[174],"with":[175,182],"draw.":[177],"In":[178],"exploratory":[180],"run":[181],"times":[184],"more":[185],"updates,":[186],"gap":[188],"between":[189],"shrinks":[194],"0.54":[196],"so":[198],"findings":[200],"concern":[201],"adaptation":[202],"limited":[205],"training":[206],"budget.":[207]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}