Cross Lingual Transfer Learning for Zero-Resource Domain Adaptation

Abstract

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 lowresource 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.

Measure and Improve Robustness in NLP Models: A Survey

“…In vision study, although the images from training distribution and test distribution can be sufficiently different, the train and test distributions mostly share the same support (the pixels are always sampled from a 0-255 integer space), although the density of these distributions can be very different (e.g., photos vs. sketches). On the other hand, domain adaptation of NLP sometimes studies the regime where the supports of the data differ, e.g., the vocabularies can be significantly different in cross-lingual studies (Abad et al, 2020;Zhang et al, 2020a).…”

Améliorations d’un système Transformer de reconnaissance de phonèmes appliqué à la parole d'enfants apprenants lecteurs

“…Pour améliorer cet état de fait, l'approche naturelle est d'adapter un modèle entraîné sur une quantité bien plus grande de parole d'adultes, en se servant de ces 13 heures comme données d'adaptation. Il s'agit de la méthode d'apprentissage par transfert (Transfer Learning, TL), très utilisée en apprentissage profond en général (Abad et al, 2020;Duan et al, 2020). Nous suivons les recommandations de (Shivakumar & Georgiou, 2020), où les auteurs suggèrent, pour de très jeunes enfants (5-8 ans), d'appliquer le TL sur l'ensemble des couches du modèle source.…”

Measure and Improve Robustness in NLP Models: A Survey

“…In vision study, although the images from training distribution and test distribution can be sufficiently different, the train and test distributions mostly share the same support (the pixels are always sample from a 0-255 integer space), although the density of these distributions can be very different (photos vs. sketches). On the other hand, domain adaptation of NLP sometimes studies the regime where the supports of the data differ (e.g., the vocabularies can be significantly different in cross-lingual study (Abad et al, 2020;Zhang et al, 2020a)).…”