most citedSpeech Synthesis as Augmentation for Low-Resource ASR

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.SDShow all

2 papers · 1 filter

cs.SD2018

An Exploration of Mimic Architectures for Residual Network Based Spectral Mapping

Peter Plantinga, Deblin Bagchi, Eric Fosler-Lussier

Spectral mapping uses a deep neural network (DNN) to map directly from noisy speech to clean speech. Our previous study found that the performance of spectral mapping improves grea…

cs.SD2018

Spectral feature mapping with mimic loss for robust speech recognition

Deblin Bagchi, Peter Plantinga, Adam Stiff +1

For the task of speech enhancement, local learning objectives are agnostic to phonetic structures helpful for speech recognition. We propose to add a global criterion to ensure de-…