Search Results for author:
Found 7 papers, 3 papers with code
ImportantAug: a data augmentation agent for speech
We introduce ImportantAug, a technique to augment training data for speech classification and recognition models by adding noise to unimportant regions of the speech and not to important regions.
Ranked #1 on
Keyword Spotting
on Google Speech Commands
(Google Speech Command-Musan metric)
Large scale evaluation of importance maps in automatic speech recognition
In this paper, we propose a metric that we call the structured saliency benchmark (SSBM) to evaluate importance maps computed for automatic speech recognizers on individual utterances.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement
In previous work, we showed that PR systems generate high quality speech for a single speaker using two neural vocoders, WaveNet and WaveGlow.
Onssen: an open-source speech separation and enhancement library
onssen is a library mainly for deep learning separation and enhancement algorithms.
Parametric Resynthesis with neural vocoders
We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression.
Speech denoising by parametric resynthesis
In comparison to two denoising systems, the oracle Wiener mask and a DNN-based mask predictor, our model equals the oracle Wiener mask in subjective quality and intelligibility and surpasses the realistic system.
