NIESR applies unsupervised adversarial invariance induction to end-to-end ASR, reporting 5.48-14.44% relative error reductions on WSJ0, CHiME3, and TIMIT without nuisance factor labels.
Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NIESR: Nuisance Invariant End-to-end Speech Recognition
NIESR applies unsupervised adversarial invariance induction to end-to-end ASR, reporting 5.48-14.44% relative error reductions on WSJ0, CHiME3, and TIMIT without nuisance factor labels.