Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach
This addresses the incremental improvement of AAC systems for audio processing applications by enabling adaptation to new data without catastrophic forgetting.
The paper tackles the problem of automated audio captioning (AAC) methods being limited to dataset-specific information by proposing a continual learning approach to adapt pre-optimized models to new audio signals without forgetting previous knowledge, achieving a good balance between learning new information and retaining old knowledge.
Automated audio captioning (AAC) is the task of automatically creating textual descriptions (i.e. captions) for the contents of a general audio signal. Most AAC methods are using existing datasets to optimize and/or evaluate upon. Given the limited information held by the AAC datasets, it is very likely that AAC methods learn only the information contained in the utilized datasets. In this paper we present a first approach for continuously adapting an AAC method to new information, using a continual learning method. In our scenario, a pre-optimized AAC method is used for some unseen general audio signals and can update its parameters in order to adapt to the new information, given a new reference caption. We evaluate our method using a freely available, pre-optimized AAC method and two freely available AAC datasets. We compare our proposed method with three scenarios, two of training on one of the datasets and evaluating on the other and a third of training on one dataset and fine-tuning on the other. Obtained results show that our method achieves a good balance between distilling new knowledge and not forgetting the previous one.