2019/10/04 by Alberto Abad, Abad, Alberto, Peter Bell +5
Engineering · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1910.02168
Submitted to ICASSP 2020. Main updates wrt previous versions: same network config in all experiments, added Babel/Material LR target language experiments, added comparison with alternative/similar methods of cross-lingual adaptation
arxiv created 2019/10/29 · arxiv updated 2019/10/31
We propose a method for zero-resource domain adaptation of DNN acoustic models, for use in low-resource situations where the only in-language training data available may be poorly matched to the intended target domain. Our method uses a multi-lingual model in which several DNN layers are shared between languages. This architecture enables domain adaptation transforms learned for one well-resourced language to be applied to an entirely different low-resource language. First, to develop the technique we use English as a well-resourced language and take Spanish to mimic a low-resource language. Experiments in domain adaptation between the conversational telephone speech (CTS) domain and broadcast news (BN) domain demonstrate a 29% relative WER improvement on Spanish BN test data by using only English adaptation data. Second, we demonstrate the effectiveness of the method for low-resource languages with a poor match to the well-resourced language. Even in this scenario, the proposed method achieves relative WER improvements of 18-27% by using solely English data for domain adaptation. Compared to other related approaches based on multi-task and multi-condition training, the proposed method is able to better exploit well-resource language data for improved acoustic modelling of the low-resource target domain.