Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition

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.