Search Results for author:
Found 6 papers, 0 papers with code
Macro-block dropout for improved regularization in training end-to-end speech recognition models
In our work, we define a macro-block that contains a large number of units from the input to a Recurrent Neural Network (RNN).
S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima
The proposed method is compared with the conventional SGD method and previous weight-noise injection algorithms using convolutional neural networks for image classification.
Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices
The RNN implementation on embedded devices can suffer from excessive DRAM accesses because the parameter size of a neural network usually exceeds that of the cache memory and the parameters are used only once for each time step.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference
As neural network algorithms show high performance in many applications, their efficient inference on mobile and embedded systems are of great interests.
FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks
The weights are quantized to 6 bits to store all of them in the on-chip memory of an FPGA.
FPGA Based Implementation of Deep Neural Networks Using On-chip Memory Only
In this work, we have developed an FPGA based fixed-point DNN system using only on-chip memory not to access external DRAM.
