Improving Self-supervised Pre-training using Accent-Specific Codebooks
This work addresses accent-related performance degradation in ASR systems, which is a domain-specific issue for speech recognition applications.
The paper tackled the problem of accent invariance in automatic speech recognition by proposing an accent-aware adaptation technique using trainable accent-specific codebooks during self-supervised pre-training, resulting in up to a 9% relative reduction in word error rate on the Mozilla Common Voice dataset.
Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems. Even with self-supervised learning and pre-training of ASR models, accent invariance is seldom achieved. In this work, we propose an accent-aware adaptation technique for self-supervised learning that introduces a trainable set of accent-specific codebooks to the self-supervised architecture. These learnable codebooks enable the model to capture accent specific information during pre-training, that is further refined during ASR finetuning. On the Mozilla Common Voice dataset, our proposed approach outperforms all other accent-adaptation approaches on both seen and unseen English accents, with up to 9% relative reduction in word error rate (WER).