1 code implementation • ICASSP 2022 • Viet Anh Trinh, Hassan Salami Kavaki, Michael I Mandel
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)
no code implementations • 21 May 2020 • Viet Anh Trinh, Michael I Mandel
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
no code implementations • 14 Nov 2019 • Soumi Maiti, Michael I Mandel
In previous work, we showed that PR systems generate high quality speech for a single speaker using two neural vocoders, WaveNet and WaveGlow.
1 code implementation • 3 Nov 2019 • Zhaoheng Ni, Michael I Mandel
onssen is a library mainly for deep learning separation and enhancement algorithms.
1 code implementation • 16 Jun 2019 • Soumi Maiti, Michael I Mandel
We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression.
no code implementations • 2 Apr 2019 • Soumi Maiti, Michael I Mandel
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.