Speaker Recognition with ResNet and VGG Networks
Authors:
- 19 April 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Various deep neural network (DNN) topologies have been recently introduced for automatic speaker recognition (SR) tasks, which tend to have ever deeper architectures. Several specific architectures have been proposed to tackle the well-known vanishing gradient issue in DNN training. We present results of experiments on text-independent SR in the wild with two deep Convolutional DNN architectures: ResNet and VGG. The results on the VoxCeleb1 benchmark database demonstrate the superiority of the ResNet solutions, in comparison with VGG and standard i-vector approaches, for speaker identification and verification in realistic acoustic conditionsKeywords
This publication has 15 references indexed in Scilit:
- Additive Margin Softmax for Face VerificationIEEE Signal Processing Letters, 2018
- Deep Coupled ResNet for Low-Resolution Face RecognitionIEEE Signal Processing Letters, 2018
- Accelerating training of DNN in distributed machine learning system with shared memory2017
- Deep Neural Network Embeddings for Text-Independent Speaker Verification2017
- VoxCeleb: A Large-Scale Speaker Identification Dataset2017
- Residual neural networks for speech recognition2017
- SphereFace: Deep Hypersphere Embedding for Face Recognition2017
- End-to-end text-dependent speaker verification2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Speaker Recognition by Machines and Humans: A tutorial reviewIEEE Signal Processing Magazine, 2015