SERIL：基于正则化增量学习的噪声自适应语音增强
SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning
摘要：
已经提出了许多噪声自适应技术来微调语音增强（SE）中的深度学习模型，以适应不匹配的噪声环境。然而，对新环境的适应可能会导致对先前学习的环境的灾难性遗忘。灾难性的遗忘问题降低了SE在现实世界的嵌入式设备中的性能，这些设备经常会重新访问以前的噪声环境。嵌入式设备的性质不允许通过额外存储所有预训练模型或早期训练数据来解决问题。在本文中，我们提出了一种基于正则化的增量学习SE（SERIL）策略，补充现有的噪声自适应策略，而无需使用额外的存储。通过正则化约束，参数被更新到新的噪声环境，同时保留先前噪声环境的知识。实验结果表明，当面对新的噪声域时，SERIL模型的性能优于未自适应的SE模型。同时，与目前基于微调的自适应技术相比，SERIL模型可以减少对先前噪声环境的遗忘52%。结果表明，SERIL模型可以有效地适应新的噪声环境，同时克服灾难性遗忘问题。这些结果使SERIL成为噪声环境频繁变化的实际SE应用的有利选择。
英文摘要：
Numerous noise adaptation techniques have been proposed to fine-tune deep-learning models in speech enhancement (SE) for mismatched noise environments. Nevertheless, adaptation to a new environment may lead to catastrophic forgetting of the previously learned environments. The catastrophic forgetting issue degrades the performance of SE in real-world embedded devices, which often revisit previous noise environments. The nature of embedded devices does not allow solving the issue with additional storage of all pre-trained models or earlier training data. In this paper, we propose a regularization-based incremental learning SE (SERIL) strategy, complementing existing noise adaptation strategies without using additional storage. With a regularization constraint, the parameters are updated to the new noise environment while retaining the knowledge of the previous noise environments. The experimental results show that, when faced with a new noise domain, the SERIL model outperforms the unadapted SE model. Meanwhile, compared with the current adaptive technique based on fine-tuning, the SERIL model can reduce the forgetting of previous noise environments by 52%. The results verify that the SERIL model can effectively adjust itself to new noise environments while overcoming the catastrophic forgetting issue. The results make SERIL a favorable choice for real-world SE applications, where the noise environment changes frequently.
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。
