Towards continually learning new languages
This addresses the need for economically beneficial continual learning in speech recognition, though it is incremental.
The paper tackled the problem of catastrophic forgetting in multilingual speech recognition when adding new languages after initial training, achieving performance for new languages comparable to training all languages at once while eliminating forgetting.
Multilingual speech recognition with neural networks is often implemented with batch-learning, when all of the languages are available before training. An ability to add new languages after the prior training sessions can be economically beneficial, but the main challenge is catastrophic forgetting. In this work, we combine the qualities of weight factorization and elastic weight consolidation in order to counter catastrophic forgetting and facilitate learning new languages quickly. Such combination allowed us to eliminate catastrophic forgetting while still achieving performance for the new languages comparable with having all languages at once, in experiments of learning from an initial 10 languages to achieve 26 languages without catastrophic forgetting and a reasonable performance compared to training all languages from scratch.