Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On the Usefulness of Diffusion-Based Room Impulse Response Interpolation to Microphone Array Processing

Sagi Della Torre, Mirco Pezzoli, Fabio Antonacci, Sharon Gannot

Abstract

Room Impulse Responses estimation is a fundamental problem in spatial audio processing and speech enhancement. In this paper, we build upon our previously introduced diffusion-based inpainting framework for Room Impulse Response interpolation and demonstrate its applicability to enhancing the performance of practical multi-microphone array processing tasks. Furthermore, we validate the robustness of this method in interpolating real-world Room Impulse Responses.

On the Usefulness of Diffusion-Based Room Impulse Response Interpolation to Microphone Array Processing

Abstract

Room Impulse Responses estimation is a fundamental problem in spatial audio processing and speech enhancement. In this paper, we build upon our previously introduced diffusion-based inpainting framework for Room Impulse Response interpolation and demonstrate its applicability to enhancing the performance of practical multi-microphone array processing tasks. Furthermore, we validate the robustness of this method in interpolating real-world Room Impulse Responses.

Paper Structure

This paper contains 8 sections, 3 equations, 7 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Problem Formulation
  3. RIR Interpolation using Inpainting
  4. Array Processing based on Interpolated RIR
  5. ATF Based MVDR Beamformer
  6. Null Steering and Interference Cancellation
  7. Generalization to Real Data
  8. Discussion

Figures (7)

  • Figure 1: System block diagram: Diffusion-based RIR reconstruction followed by beamforming for speech enhancement.
  • Figure 2: Measured (blue) and missing (orange) microphones.
  • Figure 3: Geometric setup of the room with a source and the microphone array, taken from the MeshRIR dataset.
  • Figure 4: NMSE and CD vs. mask ratio for Three Rows configuration.
  • Figure 5: NMSE and CD vs. mask ratio for Frame configuration.
  • ...and 2 more figures