Towards acoustic model unification across dialects

Mohamed Elfeky, Meysam Bastani, Xavier Velez, Pedro J. Moreno, Austin Waters

Abstract: Acoustic model performance typically decreases when evaluated on a dialectal variation of the same language that was not used during training. Similarly, models simultaneously trained on a group of dialects tend to underperform dialect-specific models. In this paper, we report on our efforts towards building a unified acoustic model that can serve a multi-dialectal language. Two techniques are presented: Distillation and MultiTask Learning (MTL). In Distillation, we use an ensemble of dialect-specific acoustic models and distill its knowledge in a single model. In MTL, we utilize multitask learning to train a unified acoustic model that learns to distinguish dialects as a side task. We show that both techniques are superior to the jointly-trained model that is trained on all dialectal data, reducing word error rates by 4:2% and 0:6%, respectively. While achieving this improvement, neither technique degrades the performance of the dialect-specific models by more than 3:4%.