Decoding Ambisonic Signals to Irregular Loudspeaker Configuration Based on Artificial Neural Networks

Authors:
Peter Wai-Ming Tsang;Wai Keung Cheung;Chi Sing Leung
Affiliations:
Dept. of Electronic Engineering, City University of Hong Kong, Hong Kong;Dept. of Electronic Engineering, City University of Hong Kong, Hong Kong;Dept. of Electronic Engineering, City University of Hong Kong, Hong Kong
Venue:
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Year:
2009

Citing 1
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper present a novel scheme which applies Artificial Neural Network (ANN) for determining the decoding parameters of a first order ambisonic system so that the three dimensional sound field can be reconstructed with an arbitrary quad speaker configuration. Differ from approaches based on the Modified Tabu Search (MTS) and the Heuristic Genetic Algorithm (HGA) which involve large number of iterations, the proposed method provides a significant reduction in computation. Experimental evaluation demonstrates that our method is significantly faster than existing schemes, and also exhibit higher accuracy and stability than the MTS.