Parametric analysis of ambisonic audio: a contributions to methods, applications and data generation

Abstract

Due to the recent advances in virtual and augmented reality, ambisonics has emerged as the de facto standard for immersive audio. Ambisonic audio can be captured using spherical microphone arrays, which are becoming increasingly popular. Yet, many methods for acoustic and microphone array signal processing are not speci cally tailored for spherical geometries. Therefore, there is still room for improvement in the eld of automatic analysis and description of ambisonic recordings. In the present thesis, we tackle this problem using methods based on the parametric analysis of the sound eld. Speci cally, we present novel contributions in the scope of blind reverberation time estimation, diffuseness estimation, and sound event localization and detection. Furthermore, several software tools developed for ambisonic dataset generation and management are also presented.