2 papers
cs.CL2022
Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition
Bethan Thomas, Samuel Kessler, Salah Karout
Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT ar…
eess.AS2021
An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning
Samuel Kessler, Bethan Thomas, Salah Karout
We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-s…