Data · dataset · 2026
Bangla Lip-to-Text Sentence Level Dataset (Processed)
Listed in Teesside University Research Data Repository
The dataset is created as follows: Step 1: Original Bangla videos were collected from YouTube Bangladesh National Television Debates and Talk Shows.
Description
Step 2: Original videos are cut into 3-second duration mini videos. Step 3: Face area from each frame of these mini videos is segmented using MediaPipe FaceMesh.
Step 4: Only those videos were chosen in which all of the frames contain exactly one face. Step 5: Audios are cut and embedded in the chosen videos (folder: Face_Only_Videos_with_Audio). Step 6: Bangla audio-to-text transcriptions of the chosen videos were generated using the Wav2Vec2 foundation model pre-trained on the Mozilla 300m Bengali Commonvoice dataset (folder: First_Transcriptions).
Read the rest (1 more)
Step 7: Videos with no transcription texts were filtered out. Step 8: A simplified transliteration for each of the translations was created (folder: Transliteration_Informal). This dataset contains only 25fps videos, has both cropped out lip videos and face videos, has all the align files in character level, has metadata, and a json file for corresponding the transcripts.
Links
Where it is published
- DOI doi.org/10.17632/wwg9kgb8cn.1 ↗
DOI / persistent id · from researchdata tees ac uk
Catalogue records · 1
- OAI-PMH record data.mendeley.com/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Adata… ↗
metadata API · from researchdata tees ac uk
Topics
Provenance · 1 source records, 11 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Teesside University Research Data Repository | oai:data.mendeley.com/wwg9kgb8cn.1 | 12 h ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].anzsrc:field:460208 | mapping · researchdata tees ac uk | vocabulary-mapper@1.0.0 | keywords['Natural Language Processing'] |
| concepts[field].anzsrc:field:460304 | mapping · researchdata tees ac uk | vocabulary-mapper@1.0.0 | keywords['Computer Vision'] |
| concepts[field].anzsrc:field:460309 | mapping · researchdata tees ac uk | vocabulary-mapper@1.0.0 | keywords['Video Processing'] |
| concepts[field].local:field:computer-science-ai | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:humanities | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| description | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/description |
| license | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/rights |
| publication_date | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| title | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/title |