Mask-Net: Learning Context Aware Invariant Features Using Adversarial Forgetting (Student Abstract)
DOI:
https://doi.org/10.1609/aaai.v37i13.27047Keywords:
ASR, Robust Speech To Text System, Adversarial Forgetting, Invariant FeaturesAbstract
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.Downloads
Published
2024-07-15
How to Cite
Yadav, H., & Ratn Shah, R. (2024). Mask-Net: Learning Context Aware Invariant Features Using Adversarial Forgetting (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16374-16375. https://doi.org/10.1609/aaai.v37i13.27047
Issue
Section
AAAI Student Abstract and Poster Program