Collection:

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct an unseen temporal slice of filterbank features from past and futu
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Videos in this product
Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct an unseen temporal slice of filterbank features from past and futu