Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition
Hsuan Su, Hua Farn, Fan-Yun Sun, Shang-Tse Chen, Hung-yi Lee
Abstract
Synthetic data is widely used in speech recognition due to the availability of text-to-speech models, which facilitate adapting models to previously unseen text domains. However, existing methods suffer in performance when they fine-tune an automatic speech recognition (ASR) model on synthetic data as they suffer from the distributional shift commonly referred to as the synthetic-to-real gap. In this paper, we find that task arithmetic is effective at mitigating this gap. Our proposed method, SYN2REAL task vector, shows an average improvement of 10.03% improvement in word error rate over baselines on the SLURP dataset. Additionally, we show that an average of SYN2REAL task vectors, when we have real speeches from multiple different domains, can further adapt the original ASR model to perform better on the target text domain.
BibTeX
@inproceedings{su-etal-2024-task,
title = "Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition",
author = "Su, Hsuan and
Farn, Hua and
Sun, Fan-Yun and
Chen, Shang-Tse and
Lee, Hung-yi",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.503/",
doi = "10.18653/v1/2024.emnlp-main.503",
pages = "8905--8915"
}