2 papers
cs.CL2023
Investigating Pre-trained Audio Encoders in the Low-Resource Condition
Hao Yang, Jinming Zhao, Gholamreza Haffari +1
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 e…
cs.CL2022
M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation
Jinming Zhao, Hao Yang, Ehsan Shareghi +1
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pr…