Blind Acoustic Room Parameter Estimation Using Phase Features

TL;DR

This paper introduces novel phase-related features for blind acoustic room parameter estimation, significantly improving accuracy over magnitude-only methods by leveraging CNNs on combined phase and magnitude data.

Contribution

It proposes the use of phase features in CNN-based models for blind room parameter estimation, extending current methods to utilize phase information for better accuracy.

Findings

Phase features outperform magnitude-only features in estimation accuracy.

The approach is effective across diverse acoustic spaces.

Multi-parameter estimation benefits from the combined phase and magnitude features.

Abstract

Modeling room acoustics in a field setting involves some degree of blind parameter estimation from noisy and reverberant audio. Modern approaches leverage convolutional neural networks (CNNs) in tandem with time-frequency representation. Using short-time Fourier transforms to develop these spectrogram-like features has shown promising results, but this method implicitly discards a significant amount of audio information in the phase domain. Inspired by recent works in speech enhancement, we propose utilizing novel phase-related features to extend recent approaches to blindly estimate the so-called "reverberation fingerprint" parameters, namely, volume and RT60. The addition of these features is shown to outperform existing methods that rely solely on magnitude-based spectral features across a wide range of acoustics spaces. We evaluate the effectiveness of the deployment of these novel features in both single-parameter and multi-parameter estimation strategies, using a novel dataset that consists of publicly available room impulse responses (RIRs), synthesized RIRs, and in-house measurements of real acoustic spaces.