143 citations · 351 across the 12 of their papers we have counts for
6 papers · 1 filter
Online Keyword Spotting with a Character-Level Recurrent Neural Network
Kyuyeon Hwang, Minjae Lee, Wonyong Sung
In this paper, we propose a context-aware keyword spotting model employing a character-level recurrent neural network (RNN) for spoken term detection in continuous speech. The RNN…
Structured Pruning of Deep Convolutional Neural Networks
Sajid Anwar, Kyuyeon Hwang, Wonyong Sung
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve…
Fixed-Point Performance Analysis of Recurrent Neural Networks
Sungho Shin, Kyuyeon Hwang, Wonyong Sung
Recurrent neural networks have shown excellent performance in many applications, however they require increased complexity in hardware or software based implementations. The hardwa…
Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification
Kyuyeon Hwang, Wonyong Sung
Connectionist temporal classification (CTC) based supervised sequence training of recurrent neural networks (RNNs) has shown great success in many machine learning areas including…
Resiliency of Deep Neural Networks under Quantization
Wonyong Sung, Sungho Shin, Kyuyeon Hwang
The complexity of deep neural network algorithms for hardware implementation can be much lowered by optimizing the word-length of weights and signals. Direct quantization of floati…
Single stream parallelization of generalized LSTM-like RNNs on a GPU
Kyuyeon Hwang, Wonyong Sung
Recurrent neural networks (RNNs) have shown outstanding performance on processing sequence data. However, they suffer from long training time, which demands parallel implementation…