Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks. These representations, however, are sensitive to distribution shifts caused by environmental factors, such as noise and/or room reverberation. Their large sizes, in turn, make them unfeasible for edge applications. In this work, we propose a knowledge distillation methodology termed RobustDistiller which compresses universal representations while making them more robust against environmental artifacts via a multi-task learning objective. The proposed layer-wise distillation recipe is evaluated on top of three well-established universal representations, as well as with three downstream tasks. Experimental results show the proposed methodology applied on top of the WavLM Base+ teacher model outperforming all other benchmarks across noise types and levels, as well as reverberation times. Oftentimes, the obtained results with the student model (24M parameters) achieved results inline with those of the teacher model (95M).

翻译：自监督语音预训练使深度神经网络模型能够从原始波形信号中捕获有意义且解耦的因子。学习到的通用语音表征可随后应用于众多下游任务。然而，这些表征对环境因素（如噪声和/或房间混响）引起的分布偏移较为敏感。同时，其庞大的规模使其难以应用于边缘设备。本文提出一种名为鲁棒蒸馏器的知识蒸馏方法，通过多任务学习目标在压缩通用表征的同时，增强其对抗环境干扰的鲁棒性。所提出的逐层蒸馏方案在三种成熟的通用表征以及三个下游任务上进行了评估。实验结果表明，基于WavLM Base+教师模型所提出的方法在各类噪声类型、噪声水平及混响时间下均优于所有其他基准。学生模型（2400万参数）所取得的结果常与教师模型（9500万参数）持平。