Dimensionality reduction using Isomap applied to spatial audio

Author(s)

Felipe Leonel Grijalva Arévalo

• Document type: Master's Dissertation
• Press: Campinas, SP.
• Institution: Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação
• Defense date: 2014-07-29

Examining board members

Luiz César Martini; José Antonio dos Santos Borges; Yuzo Iano

• Advisor: Siome Klein Goldenstein; Luiz César Martini

Abstract

As auditory augmented reality applications become more important, there is increasing effort in spatial audio research. The term spatial audio refers to techniques where a person's anatomy (i.e. the pinnae, head and torso) is modeled as digital filters. By filtering a sound source with these filters, a listener is capable of perceiving a sound as though it were reproduced at a specific spatial location. In the frequency domain, these filters are known as Head-Related Transfer Functions (HRTFs). This thesis states the basic principles of spatial audio and provides an analysis of the spectral characteristics of HRTFs. Moreover, since these spectral features differ among individuals, we introduce a new anthropometric-based method for customizing of HRTFs in the horizontal plane. The method uses Isomap, artificial neural networks (ANN), and a neighborhood-based reconstruction procedure. We first modify Isomap's graph construction step to emphasize the individuality of HRTFs and perform a customized nonlinear dimensionality reduction of the HTRFs. We then use an ANN to model the nonlinear relationship between anthropometric features and our low-dimensional HRTFs. Finally, we use a neighborhood-based reconstruction approach to reconstruct the HRTF from the estimated low-dimensional version. Simulations show that our approach performs better than PCA (Principal Component Analysis) and confirm that Isomap is capable of discovering the underlying nonlinear relationships of sound perception (AU)

• FAPESP's process: 13/21349-1 - Vision for the blind: translating 3D visual concepts into 3D auditory clues
• Grantee: Felipe Leonel Grijalva Arévalo
• Support Opportunities: Scholarships in Brazil - Master