DOIONLINE

DOIONLINE NO - IJACEN-IRAJ-DOIONLINE-13839

Publish In
International Journal of Advance Computational Engineering and Networking (IJACEN)-IJACEN
Journal Home
Volume Issue
Issue
Volume-6, Issue-10  ( Oct, 2018 )
Paper Title
Deep Neural Network-Based Sound Localization using Interaural Correlation and Synchronized ILD
Author Name
Hyeon Tae Hwang, Deokgyu Yun, Seung Ho Choi
Affilition
Dept. of Electronic and IT Media Engineering, Seoul National University of Science and Technology Dept. of Electronic Engineering, Seoul National University of Science and Technology
Pages
53-54
Abstract
This study is about sound localization based on deep neural network (DNN) using interaural cross-correlation coefficients and interaural level difference (ILD) as feature parameters. Especially, we propose a synchronized ILD that eliminates the difference of interaural arrival time. The proposed method shows better performance than the conventional method through various experiments in clean and noisy environments. Index Terms - Deep Neural Network, Sound Localization, Interaural Correlation, Synchronized ILD
  View Paper