Sparse Architectures for Text-Independent Speaker Verification Using Deep Neural Networks

Autor:	Sedighi, Sara, Ramhormozi, Shayan
Rok vydání:	2018
Předmět:	Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1805.07628 Zobrazit plný text záznamu View this record from Arxiv