Meta Learning for End-to-End Low-Resource Speech Recognition
This addresses the problem of limited data for speech recognition in low-resource languages, though it is incremental as it applies an existing meta-learning algorithm to a new domain.
The authors tackled low-resource automatic speech recognition by meta-learning initialization parameters from multiple languages to adapt quickly to unseen languages, achieving significant improvements over state-of-the-art multitask pretraining across all target languages.
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.