Existing auto-regressive language models have demonstrated a remarkable capability to perform a new task with just a few examples in prompt, without requiring any additional training. In order to extend this capability to a multi-modal setting (i.e. speech and language), this paper introduces the Seal model, an abbreviation for speech language model. It incorporates a novel alignment method, in which Kullback-Leibler divergence loss is performed to train a projector that bridges a frozen speech encoder with a frozen language model decoder. The resulting Seal model exhibits robust performance as a few-shot learner on two speech understanding tasks. Additionally, consistency experiments are conducted to validate its robustness on different pre-trained language models.
@article{arxiv.2407.14875,
title = {Seal: Advancing Speech Language Models to be Few-Shot Learners},
author = {Shuyu Lei and Lingen Liu and Jiaolong Yang and Yasen Jiao and Yuxiang Yang and Yushu Yang and Xiang Guo},
journal= {arXiv preprint arXiv:2407.14875},
year = {2024}
}