-
Noisy Training Improves E2E ASR for the Edge
Automatic speech recognition (ASR) has become increasingly ubiquitous on...
07/09/2021 ∙ by Dilin Wang, et al. ∙
0
∙
share
read it
-
Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
When tuning the architecture and hyperparameters of large machine learni...
06/22/2021 ∙ by David Eriksson, et al. ∙
10
∙
share
read it
-
Collaborative Training of Acoustic Encoders for Speech Recognition
On-device speech recognition requires training models of different sizes...
06/16/2021 ∙ by Varun Nagaraja, et al. ∙
0
∙
share
read it
-
Accelerating Sparse Deep Neural Networks
As neural network model sizes have dramatically increased, so has the in...
04/16/2021 ∙ by Asit Mishra, et al. ∙
0
∙
share
read it
-
Memory-efficient Speech Recognition on Smart Devices
Recurrent transducer models have emerged as a promising solution for spe...
02/23/2021 ∙ by Ganesh Venkatesh, et al. ∙
0
∙
share
read it
-
Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Current state-of-the-art approaches for Semi-supervised Video Object Seg...
12/21/2020 ∙ by Hyojin Park, et al. ∙
0
∙
share
read it
-
Can Temporal Information Help with Contrastive Self-Supervised Learning?
Leveraging temporal information has been regarded as essential for devel...
11/25/2020 ∙ by Yutong Bai, et al. ∙
10
∙
share
read it
-
TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Semi-supervised video object segmentation (semi-VOS) is widely used in m...
11/09/2020 ∙ by Hyojin Park, et al. ∙
4
∙
share
read it
-
Mixed Precision Training
Deep neural networks have enabled progress in a wide variety of applicat...
10/10/2017 ∙ by Paulius Micikevicius, et al. ∙
0
∙
share
read it
-
Accelerating Deep Convolutional Networks using low-precision and sparsity
We explore techniques to significantly improve the compute efficiency an...
10/02/2016 ∙ by Ganesh Venkatesh, et al. ∙
0
∙
share
read it
