Improvement of accuracy in a sound synthesis method using Evolutionary Product Unit Networks

Research areas:

• Methodology - Machine learning

Year:

2013

Type of Publication:

Article

Authors:

• Redel-Macías, M. D.
• Fernandez-Navarro, Francisco
• Gutiérrez, Pedro Antonio
• Cubero-Atienza, A. J.
• Hervás-Martínez, César

Journal:

Expert Systems with Applications

Volume:

40

Number:

5

Pages:

1477-1483

ISSN:

0957-4174

BibTex:

@article{ESWARuido2013, author = "M. D. Redel-Mac{\'i}as and Francisco Fernandez-Navarro and Pedro Antonio Guti{\'e}rrez and A. J. Cubero-Atienza and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "Auralization through binaural transfer path analysis and synthesis is a useful tool to analyze how contributions from different sources affect the perception of sound. This paper presents a novel model based on the auralization of sound sources through the study of the behavior of the system with respect to frequency. The proposed approach is a combined model using the airborne source quantification (ASQ) technique for low-mid frequencies (lower equal than.5 kHz) and Evolutionary Product-Unit Neural Networks (EPUNNs) for high frequencies ({\&}gt;2.5 kHz), which improve overall accuracy. The accuracy of all models has been evaluated in terms of the Mean Squared Error (MSE) and the Standard Error of Prediction (SEP), the combined model obtaining the smallest value for high frequencies. Moreover, the best prediction model was established based on sound quality metrics, the proposed method showing better accuracy than the ASQ technique at high frequencies in terms of loudness, sharpness and 1/3rd octave bands.", awards = "JCR (2013): 1.965 (category OPERATIONS RESEARCH {\&}amp; MANAGEMENT SCIENCE, position 11/79 Q1)", comments = "JCR (2013): 1.965 (category OPERATIONS RESEARCH {\&}amp; MANAGEMENT SCIENCE, position 11/79 Q1)", doi = "10.1016/j.eswa.2012.08.041", issn = "0957-4174", journal = "Expert Systems with Applications", note = "JCR (2013): 1.965 (category OPERATIONS RESEARCH {\&}amp; MANAGEMENT SCIENCE, position 11/79 Q1)", number = "5", pages = " 1477--1483", title = "{I}mprovement of accuracy in a sound synthesis method using {E}volutionary {P}roduct {U}nit {N}etworks", url = "http://dx.doi.org/10.1016/j.eswa.2012.08.041", volume = "40", year = "2013", }

Note:

JCR (2013): 1.965 (category OPERATIONS RESEARCH & MANAGEMENT SCIENCE, position 11/79 Q1)

Abstract:

Auralization through binaural transfer path analysis and synthesis is a useful tool to analyze how contributions from different sources affect the perception of sound. This paper presents a novel model based on the auralization of sound sources through the study of the behavior of the system with respect to frequency. The proposed approach is a combined model using the airborne source quantification (ASQ) technique for low-mid frequencies (lower equal than.5 kHz) and Evolutionary Product-Unit Neural Networks (EPUNNs) for high frequencies (>2.5 kHz), which improve overall accuracy. The accuracy of all models has been evaluated in terms of the Mean Squared Error (MSE) and the Standard Error of Prediction (SEP), the combined model obtaining the smallest value for high frequencies. Moreover, the best prediction model was established based on sound quality metrics, the proposed method showing better accuracy than the ASQ technique at high frequencies in terms of loudness, sharpness and 1/3rd octave bands.

Comments:

JCR (2013): 1.965 (category OPERATIONS RESEARCH & MANAGEMENT SCIENCE, position 11/79 Q1)