Bottleneck features from SNR-adaptive denoising deep classifier for speaker identification

Abstract

In this paper, we explore the potential of using deep learning for extracting speaker-dependent features for noise robust speaker identification. More specifically, an SNR-adaptive denoising classifier is constructed by stacking two layers of restricted Boltzmann machines (RBMs) on top of a denoising deep autoencoder, where the top-RBM layer is connected to… (More)
DOI: 10.1109/APSIPA.2015.7415429

Topics

6 Figures and Tables

Slides referencing similar topics