Sparse Architectures for Text-Independent Speaker Verification Using Deep Neural Networks
arXiv:1805.07628
Abstract
Network pruning is of great importance due to the elimination of the unimportant weights or features activated due to the network over-parametrization. Advantages of sparsity enforcement include preventing the overfitting and speedup. Considering a large number of parameters in deep architectures, network compression becomes of critical importance due to the required huge amount of computational power. In this work, we impose structured sparsity for speaker verification which is the validation of the query speaker compared to the speaker gallery. We will show that the mere sparsity enforcement can improve the verification results due to the possible initial overfitting in the network.
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Learning in Neural Networks: An Overview
- Distilling the Knowledge in a Neural Network
- VoxCeleb: a large-scale speaker identification dataset
- Predicting Parameters in Deep Learning
- Learning Structured Sparsity in Deep Neural Networks
- Memory Bounded Deep Convolutional Networks
- SpeechPy - A Library for Speech Processing and Recognition