RobustDistiller：压缩通用语音表示以增强环境鲁棒性
RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness
摘要：
自我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的和分离的因素。然后，学习到的通用语音表示可以用于许多下游任务。然而，这些表示对由环境因素（诸如噪声和/或房间混响）引起的分布偏移敏感。反过来，它们的大尺寸使它们不适合边缘应用。在这项工作中，我们提出了一种知识蒸馏方法，称为RobustDistiller，它压缩了通用表示，同时通过多任务学习目标使它们对环境文物更加鲁棒。建议的分层蒸馏配方上的三个公认的通用表示，以及与三个下游任务进行评估。实验结果表明，在WavLM Base+教师模型之上应用的所提出的方法在噪声类型和级别以及混响时间方面优于所有其他基准。通常，学生模型（24 M参数）获得的结果与教师模型（95 M）的结果一致。
英文摘要：
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).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
