Adversarial Augmentation For Adapter Learning

Jen Tzung Chien*, Wei Yu Sun

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The recent pre-trained models have achieved state-of-the-art results for natural language understanding (NLU) and automatic speech recognition (ASR). However, the pre-trained models likely suffer from the overfitting problem when adapting the model to a low-resource target domain. This study handles this low-resource setting by training an adversarial adapter based on a pre-trained backbone model. The adversarial training is performed by implementing the data augmentation rather than enhancing the adversarial robustness. The proposed method leverages adversarial training to collect augmented data to reinforce adapter learning with a smoothed decision boundary. The size of trainable parameters is tightly controlled to alleviate the overfitting to enhance the model capability. In the experiments, this work considerably improves the performance in NLU tasks. The adversarial adapter learning is further extended for ASR to show the merit of this method in terms of efficiency and accuracy.

Original languageEnglish
Title of host publication2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350306897
DOIs
StatePublished - 2023
Event2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 - Taipei, Taiwan
Duration: 16 Dec 202320 Dec 2023

Publication series

Name2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

Conference

Conference2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
Country/TerritoryTaiwan
CityTaipei
Period16/12/2320/12/23

Keywords

  • adapter learning
  • adversarial training
  • data augmentation
  • fine-tuning
  • pre-trained model

Fingerprint

Dive into the research topics of 'Adversarial Augmentation For Adapter Learning'. Together they form a unique fingerprint.

Cite this