论文标题
使用适配器克服端到端自动语音识别中的灾难性遗忘
Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
论文作者
论文摘要
对人工神经网络学习一组任务仍然是一个挑战，在这种情况下，该网络往往会遭受灾难性遗忘（CF）的困扰。端到端（E2E）自动语音识别（ASR）模型也适用于单语任务。在本文中，我们旨在通过插入适配器，几个参数的小架构来克服E2E ASR的CF，这些参数可以将通用模型细化为特定任务，并将其纳入我们的模型中。我们使这些适配器特定于任务，同时将所有任务共享的模型参数正规化，从而刺激模型以充分利用适配器，同时使共享参数可以很好地适用于所有任务。我们的方法的表现优于两个单语实验的所有基准，同时更有效地存储，而无需从以前的任务中存储数据。
Learning a set of tasks in sequence remains a challenge for artificial neural networks, which, in such scenarios, tend to suffer from Catastrophic Forgetting (CF). The same applies to End-to-End (E2E) Automatic Speech Recognition (ASR) models, even for monolingual tasks. In this paper, we aim to overcome CF for E2E ASR by inserting adapters, small architectures of few parameters which allow a general model to be fine-tuned to a specific task, into our model. We make these adapters task-specific, while regularizing the parameters of the model shared by all tasks, thus stimulating the model to fully exploit the adapters while keeping the shared parameters to work well for all tasks. Our method outperforms all baselines on two monolingual experiments while being more storage efficient and without requiring the storage of data from previous tasks.
