Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a visually-ground speech model, notably eliminating the need for speech-text paired data. Our experimental results on four spoken language understanding (SLU) benchmarks suggest the superiority of our model in capturing semantic information.

翻译：近期自监督语音模型的进展在诸多下游任务中展现出显著性能提升。然而，这类模型主要聚焦于帧级训练目标，在需要语义理解的口语理解任务中存在局限性。现有研究通常依赖额外的语音-文本数据作为中间目标，这在现实场景中成本高昂。针对这一挑战，我们提出伪词级HuBERT（PW-HuBERT）框架，该框架将源自视觉引导语音模型的伪词级目标融入训练过程，显著消除了对语音-文本配对数据的依赖。我们在四个口语理解（SLU）基准任务上的实验结果表明，本模型在捕获语义信息方面具有显著优势。