Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks. Nonetheless, the capabilities of these encoders in low-resource settings are yet to be thoroughly explored. To address this, we conduct a comprehensive set of experiments using a representative set of 3 state-of-the-art encoders (Wav2vec2, WavLM, Whisper) in the low-resource setting across 7 speech understanding and generation tasks. We provide various quantitative and qualitative analyses on task performance, convergence speed, and representational properties of the encoders. We observe a connection between the pre-training protocols of these encoders and the way in which they capture information in their internal layers. In particular, we observe the Whisper encoder exhibits the greatest low-resource capabilities on content-driven tasks in terms of performance and convergence speed.
@article{arxiv.2305.17733,
title = {Investigating Pre-trained Audio Encoders in the Low-Resource Condition},
author = {Hao Yang and Jinming Zhao and Gholamreza Haffari and Ehsan Shareghi},
journal= {arXiv preprint arXiv:2305.17733},
year = {2023}
}