Fine-Tuning SLAM-ASR for Low-Resource Language Speech Recognition with High-Resource Alignment

Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, their applicability is still less explored in low-resource settings. This work investigates the use of Speech LLMs for low-resource Automatic Speech Recognition using the SLAM-ASR framework, where a trainable lightweight projector connects a speech encoder and a LLM. Firstly, we assess training data volume requirements to match Whisper-only performance, re-emphasizing the challenges of limited data. Secondly, we show th Research goal: What is the impact of fine-tuning SLAM-ASR on low-resource language speech recognition when the LLM is first aligned with high-resource language speech data vs. text data? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.