Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation
Danilo de OliveiraTimo Gerkmann
Danilo de OliveiraTimo Gerkmann
Sep 2023
0被引用
0笔记
开学季活动火爆进行中，iPad、蓝牙耳机、拍立得、键盘鼠标套装等你来拿
摘要原文
Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge distillation (and its more recently proposed extension, decoupled knowledge distillation) can be applied to the task of distilling HuBERT. In contrast to methods that focus on distilling internal features, this allows for more freedom in the network architecture of the compressed model. We thus propose to distill HuBERT's Transformer layers into an LSTM-based distilled model that reduces the number of parameters even below DistilHuBERT and at the same time shows improved performance in automatic speech recognition.
