Group Relative Policy Optimisation Improves Multilingual Speech Recognition in Low-Resource Languages
Autoregressive encoder-decoder speech recognition models trained with teacher forcing can suffer from exposure bias, limiting their ability to recover from their own prediction errors at inference time.
By Tim Wenjie Hu, Evelyn Nafula Ouma, Benjamin Akera, John A. QuinnarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 23, 2026.
Comments
Sign in to join the discussion.