Learning Fast Adaptation on Cross-Accented Speech Recognition

Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Peng Xu, Pascale Fung

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents create a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system. In this paper, we introduce a cross-accented English speech recognition task as a benchmark for measuring the ability of the model to adapt to unseen accents using the existing CommonVoice corpus. We also propose an accent-agnostic approach that extends the model-agnostic meta-learning (MAML) algorithm for fast adaptation to unseen accents. Our approach significantly outperforms joint training in both zero-shot, few-shot, and all-shot in the mixed-region and cross-region settings in terms of word error rate.

 DOI: 10.21437/Interspeech.2020-0045

Cite as: Winata, G.I., Cahyawijaya, S., Liu, Z., Lin, Z., Madotto, A., Xu, P., Fung, P. (2020) Learning Fast Adaptation on Cross-Accented Speech Recognition. Proc. Interspeech 2020, 1276-1280, DOI: 10.21437/Interspeech.2020-0045.

  author={Genta Indra Winata and Samuel Cahyawijaya and Zihan Liu and Zhaojiang Lin and Andrea Madotto and Peng Xu and Pascale Fung},
  title={{Learning Fast Adaptation on Cross-Accented Speech Recognition}},
  booktitle={Proc. Interspeech 2020},