Speech-based Slot Filling using Large Language Models
It addresses the challenge of improving spoken language understanding accuracy in noisy conditions for applications like voice assistants, though it is incremental in adapting existing LLMs.
This paper tackles the problem of slot filling with noisy automatic speech recognition (ASR) transcriptions by applying large language models (LLMs) through in-context learning and fine-tuning, achieving an 8.3% absolute SLU-F1 improvement over a baseline system on limited data.
Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs to slot filling with noisy ASR transcriptions, via both in-context learning and task-specific fine-tuning. Dedicated prompt designs and fine-tuning approaches are proposed to improve the robustness of LLMs for slot filling with noisy ASR transcriptions. Moreover, a linearised knowledge injection (LKI) scheme is also proposed to integrate dynamic external knowledge into LLMs. Experiments were performed on SLURP to quantify the performance of LLMs, including GPT-3.5-turbo, GPT-4, LLaMA-13B and Vicuna-13B (v1.1 and v1.5) with different ASR error rates. The use of the proposed fine-tuning together with the LKI scheme for LLaMA-13B achieved an 8.3% absolute SLU-F1 improvement compared to the strong Flan-T5-base baseline system on a limited data setup.