Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses. (arXiv:2210.11642v1 [cs.CL])

We propose a novel method that combines CycleGAN and inter-domain losses for
semi-supervised end-to-end automatic speech recognition. Inter-domain loss
targets the extraction of an intermediate shared representation of speech and
text inputs using a shared network. CycleGAN uses cycle-consistent loss and the
identity mapping loss to preserve relevant characteristics of the input feature
after converting from one domain to another. As such, both approaches are
suitable to train end-to-end models on unpaired speech-text inputs. In this
paper, we exploit the …

arxiv automatic speech recognition cyclegan losses semi-supervised speech speech recognition