https://scholars.lib.ntu.edu.tw/handle/123456789/640018
Title: | Prompting and Adapter Tuning For Self-Supervised Encoder-Decoder Speech Model | Authors: | Chang, Kai Wei Chen, Ming Hsin Lin, Yun Ping Hsu, Jing Neng Huang, Paul Kuo Ming Huang, Chien Yu Li, Shang Wen HUNG-YI LEE |
Keywords: | adapter | automatic speech recognition | parameter-efficient tuning | Prompting | sequence generation | Issue Date: | 1-Jan-2023 | Source: | 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 | Abstract: | Prompting and adapter tuning have emerged as efficient alternatives to fine-tuning (FT) methods. However, existing studies on speech prompting focused on classification tasks and failed on more complex sequence generation tasks. Besides, adapter tuning is primarily applied with a focus on encoder-only self-supervised models. Our experiments show that prompting on Wav2Seq, a self-supervised encoder-decoder model, surpasses previous works in sequence generation tasks. It achieves a remarkable 53% relative improvement in word error rate for ASR and a 27% in F1 score for slot filling. Additionally, prompting competes with the FT method in the low-resource scenario. Moreover, we show the transferability of prompting and adapter tuning on Wav2Seq in cross-lingual ASR. When limited trainable parameters are involved, prompting and adapter tuning consistently outperform conventional FT across 7 languages. Notably, in the low-resource scenario, prompting consistently outperforms adapter tuning. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/640018 | ISBN: | 9798350306897 | DOI: | 10.1109/ASRU57964.2023.10389731 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.