Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition

no code implementations • 21 Oct 2021 • Ting-yao Hu, Mohammadreza Armandpour, Ashish Shrivastava, Jen-Hao Rick Chang, Hema Koppula, Oncel Tuzel

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation

no code implementations • 2 Nov 2020 • Ting-yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang, Hema Koppula, Stefan Braun, Kyuyeon Hwang, Ozlem Kalinli, Oncel Tuzel

Our policy adapts the augmentation parameters based on the training loss of the data samples.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Hallucinated Humans as the Hidden Context for Labeling 3D Scenes

no code implementations • CVPR 2013 • Yun Jiang, Hema Koppula, Ashutosh Saxena

Given only a dataset of scenes containing objects but not humans, we show that our algorithm can recover the human object relationships.

Attribute Object +1