In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering. We show that these concepts complement each other and result in a strong representation learning model for speech. DinoSR first extracts contextualized embeddings from the input audio with a teacher network, then runs an online clustering system on the embeddings to yield a machine-discovered phone inventory, and finally uses the discretized tokens to guide a student network. We show that DinoSR surpasses previous state-of-the-art performance in several downstream tasks, and provide a detailed analysis of the model and the learned discrete units.

翻译：本文提出了一种结合掩码语言建模、自蒸馏与在线聚类的自监督语音表征学习方法（DinoSR）。研究表明，这些技术相互协同，能够构建强大的语音表征学习模型。DinoSR首先通过教师网络从输入音频中提取上下文感知的嵌入表示，随后对这些嵌入进行在线聚类处理，生成机器发现的音素库，最终利用离散化标记指导学生网络。实验表明，DinoSR在多项下游任务中超越了先前最先进的性能水平，并对模型及其学习的离散单元进行了详细分析。