Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning
This work addresses speech processing researchers by systematically exploring multi-task finetuning for speech, though it appears incremental as it builds on existing self-supervised and multi-task methods.
The paper tackles the problem of improving speech representation learning by combining self-supervised pretraining with supervised multi-task finetuning, showing that this approach enhances performance on downstream tasks.
Speech representation learning plays a vital role in speech processing. Among them, self-supervised learning (SSL) has become an important research direction. It has been shown that an SSL pretraining model can achieve excellent performance in various downstream tasks of speech processing. On the other hand, supervised multi-task learning (MTL) is another representation learning paradigm, which has been proven effective in computer vision (CV) and natural language processing (NLP). However, there is no systematic research on the general representation learning model trained by supervised MTL in speech processing. In this paper, we show that MTL finetuning can further improve SSL pretraining. We analyze the generalizability of supervised MTL finetuning to examine if the speech representation learned by MTL finetuning can generalize to unseen new tasks.