AAAI 2023technical1 citations
Mask-Net: Learning Context Aware Invariant Features Using Adversarial Forgetting (Student Abstract)
Abstract
Training a robust system, e.g., Speech to Text (STT), requires large datasets. Variability present in the dataset, such as unwanted nuances and biases, is the reason for the need for large datasets to learn general representations. In this work, we propose a novel approach to induce invariance using adversarial forgetting (AF). Our initial experiments on learning invariant features such as accent on the STT task achieve better generalizations in terms of word error rate (WER) compared to traditional models. We observe an absolute improvement of 2.2% and 1.3% on out-of-distribution and in-distribution test sets, respectively.
BibTeX
@article{Yadav_Ratn Shah_2024, title={Mask-Net: Learning Context Aware Invariant Features Using Adversarial Forgetting (Student Abstract)}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/27047}, DOI={10.1609/aaai.v37i13.27047}, abstractNote={Training a robust system, e.g., Speech to Text (STT), requires large datasets. Variability present in the dataset, such as unwanted nuances and biases, is the reason for the need for large datasets to learn general representations. In this work, we propose a novel approach to induce invariance using adversarial forgetting (AF). Our initial experiments on learning invariant features such as accent on the STT task achieve better generalizations in terms of word error rate (WER) compared to traditional models. We observe an absolute improvement of 2.2% and 1.3% on out-of-distribution and in-distribution test sets, respectively.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Yadav, Hemant and Ratn Shah, Rajiv}, year={2024}, month={Jul.}, pages={16374-16375} }