MétaCan
Menu
Back to cohort
Record W7133348273 · doi:10.65521/ijacect.v14i3s.1592

PolySub : AI-Powered Multilingual Subtitle and Dubbing with GenAI

2025· article· W7133348273 on OpenAlexaff
Varad Joshi, Astha Asati, Taufique Sana, Siddharth Gajbhiye, Hansaraj Wankhede

Bibliographic record

VenueInternational Journal on Advanced Computer Engineering and Communication Technology · 2025
Typearticle
Language
FieldArts and Humanities
TopicSubtitles and Audiovisual Media
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsSubtitleLimit (mathematics)Interpretation (philosophy)Machine translation

Abstract

fetched live from OpenAlex

Language barriers go beyond communication gaps; they can restrict access to knowledge, limit collaboration, and reduce the global reach of digital content. PolySub addresses this challenge by providing an AI-powered platform for multi- lingual subtitling and dubbing, enabling seamless cross-language video accessibility. The system integrates OpenAI Whisper for transcription, Meta NLLB for translation and Meta MMS (TTS) model for audio generation, producing SRT files, dubbed videos with subtitles and original videos with embedded subtitles as outputs. Designed for scale, PolySub supports more than 150 languages, ensuring accessibility for diverse audiences. Evalua- tion shows strong performance, achieving a BLEU score of 37.0 and a BERTScore of 85.8, reflecting accurate, fluent, and se- mantically consistent output. This paper presents the conceptual framework of PolySub, outlines its architecture, and highlights how automated multilingual pipelines can enhance accessibility, scalability, and global communication across education, media, and professional domains.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.849
Threshold uncertainty score0.872

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.005
GPT teacher head0.248
Teacher spread0.242 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueInternational Journal on Advanced Computer Engineering and Communication TechnologySame topicSubtitles and Audiovisual MediaFrench-language works237,207