{"id":"https://openalex.org/W7214746006","doi":"https://doi.org/10.5281/zenodo.23036344","title":"The First Character-Level Visual Speech Recognition for Bangla: data and code","display_name":"The First Character-Level Visual Speech Recognition for Bangla: data and code","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214746006","doi":"https://doi.org/10.5281/zenodo.23036344"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23036344","doi":"https://doi.org/10.5281/zenodo.23036344","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23036344","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},"volume":null,"type":"software","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23036344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007827368","display_name":"Abdul Hasib Uddin","orcid":"https://orcid.org/0000-0003-1000-2600","observed_orcids":["https://orcid.org/0000-0003-1000-2600"]},"institutions":[{"id":"https://openalex.org/I124386471","display_name":"Khulna University","ror":"https://ror.org/05pny7s12","country_code":"BD","type":"education","lineage":["https://openalex.org/I124386471"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Uddin, Abdul Hasib","raw_affiliation_strings":["Computer Science and Engineering Discipline, Khulna University, Khulna-9208, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Discipline, Khulna University, Khulna-9208, Bangladesh","institution_ids":["https://openalex.org/I124386471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067587924","display_name":"Abu Shamim Mohammad Arif","orcid":"https://orcid.org/0000-0003-4627-6793","observed_orcids":["https://orcid.org/0000-0003-4627-6793"]},"institutions":[{"id":"https://openalex.org/I124386471","display_name":"Khulna University","ror":"https://ror.org/05pny7s12","country_code":"BD","type":"education","lineage":["https://openalex.org/I124386471"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Arif, Abu Shamim Mohammad","raw_affiliation_strings":["Computer Science and Engineering Discipline, Khulna University, Khulna-9208, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Discipline, Khulna University, Khulna-9208, Bangladesh","institution_ids":["https://openalex.org/I124386471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I124386471"],"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/T10860","display_name":"Speech and Audio Processing","score":0.7817000150680542,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7817000150680542,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.15639999508857727,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.013299999758601189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/visual-speech-recognition","display_name":"visual speech recognition","score":0.9279999732971191},{"id":"https://openalex.org/keywords/bengali-language","display_name":"Bengali language","score":0.8709999918937683},{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.6930000185966492},{"id":"https://openalex.org/keywords/character-error-rate","display_name":"character error rate","score":0.7940000295639038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7009000182151794},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6061999797821045},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5055000185966492},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.3702999949455261},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.3467999994754791},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23036344","doi":"https://doi.org/10.5281/zenodo.23036344","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23036344","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},{"id":"doi:10.5281/zenodo.23036345","doi":"https://doi.org/10.5281/zenodo.23036345","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23036345","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23036344","doi":"https://doi.org/10.5281/zenodo.23036344","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23036344","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},"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":["https://openalex.org/W7215087090","https://openalex.org/W2311797044","https://openalex.org/W7223083348","https://openalex.org/W3216563855","https://openalex.org/W7155104846","https://openalex.org/W7096095595","https://openalex.org/W3081743816","https://openalex.org/W7221647536","https://openalex.org/W2408292052","https://openalex.org/W2895411524"],"abstract_inverted_index":{"Pre-print:":[0],"https://doi.org/10.21203/rs.3.rs-11207165/v1Prediction":[1],"files,":[2],"training":[3,19],"record,":[4],"and":[5,48],"scoring":[6],"code":[7,46],"behind":[8],"the":[9,68],"first":[10],"character-level":[11],"visual":[12],"speech":[13],"recognition":[14],"work":[15],"for":[16],"Bangla.":[17],"Five":[18],"seeds":[20],"of":[21],"a":[22,56],"visual-only":[23],"character":[24,42],"transducer":[25],"on":[26],"14,431":[27],"LipBengal":[28],"test":[29],"clips":[30],"from":[31,67],"30":[32],"held-out":[33],"speakers:":[34],"78.15":[35],"+/-":[36,40,50],"1.45%":[37],"charWER,":[38],"63.48":[39],"0.79%":[41],"error":[43],"over":[44,52],"Unicode":[45],"points":[47],"71.73":[49],"0.98%":[51],"grapheme":[53],"clusters,":[54],"against":[55],"99.79%":[57],"majority-class":[58],"floor.":[59],"The":[60],"included":[61],"script":[62],"recomputes":[63],"all":[64],"three":[65],"rates":[66],"prediction":[69],"files.":[70]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-30T00:00:00"}
