Pith. sign in

Leveraging broadcast media subtitle transcripts for automatic speech recognition and subtitling,

Jakob Poncelet, Hugo Van hamme, “Leveraging broadcast media subtitle transcripts for automatic speech recognition, subtitling,” arXiv:2502 · 2025 · arXiv 2502.03212

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

eess.AS 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Phoneme-First Prediction for LLM-Based Speech Recognition

eess.AS · 2026-06-09 · unverdicted · novelty 5.0

Integrating an explicit phoneme-prediction step into an LLM-based speech recognizer improves transcription accuracy and acoustic faithfulness, especially in low-resource conditions.

citing papers explorer

Showing 1 of 1 citing paper.

  • Phoneme-First Prediction for LLM-Based Speech Recognition eess.AS · 2026-06-09 · unverdicted · none · ref 39

    Integrating an explicit phoneme-prediction step into an LLM-based speech recognizer improves transcription accuracy and acoustic faithfulness, especially in low-resource conditions.