Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition
This work addresses the challenge of enhancing ASR accuracy for applications in speech processing, representing an incremental advancement over existing single-stage pre-training methods.
The paper tackles the problem of improving automatic speech recognition (ASR) performance by introducing a multi-stage pre-training method that combines multi-modal and multi-task unsupervised pre-training with supervised mid-training, resulting in relative word error rate improvements of up to 38.45% over baselines on datasets like Librispeech and SUPERB.
Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks. Existing multi-modal pre-training methods for the ASR task have primarily focused on single-stage pre-training where a single unsupervised task is used for pre-training followed by fine-tuning on the downstream task. In this work, we introduce a novel method combining multi-modal and multi-task unsupervised pre-training with a translation-based supervised mid-training approach. We empirically demonstrate that such a multi-stage approach leads to relative word error rate (WER) improvements of up to 38.45% over baselines on both Librispeech and SUPERB. Additionally, we share several important findings for choosing pre-training methods and datasets.