Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems

• Published in: arXiv.org
• Main Authors: Chin Yuen Kwok, Jia Qi Yip, Chng, Eng Siong
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 27.09.2024
• Subjects: Cognitive tasks; Computer Science - Computation and Language; Computer Science - Sound; Computer vision; Freezing; Languages
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2407.03645

Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL methods, mainly designed for computer vision and reinforcement learning tasks, often yield sub-optimal results when directly applied to MASR. We hypothesise that this is because CL of the auto-regressive decoder in the MASR model is difficult. To verify this, we propose four optimizations on the decoder. They include decoder-layer gradient surgery, freezing unused token embeddings, suppressing output of newly added tokens, and learning rate re-scaling. Our experiments on adapting Whisper to 10 unseen languages from the Common Voice dataset demonstrate that these optimizations reduce the Average Word Error Rate (AWER) of pretrained languages from 14.2% to 12.4% compared with Experience Replay, without compromising the AWER of new languages.