ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models

Researchers introduced ReHear, a framework for refining pseudo-labels in semi-supervised speech recognition using an audio-aware large language model. This approach reduces errors by iteratively improving pseudo-label accuracy through integration of both ASR hypotheses and source audio, leading to better performance than existing methods. Content creators can benefit from more accurate automatic transcription tools for their audio content.

Read the full article at arXiv cs.CL (NLP)

---

Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.