Blind Acoustic Room Parameter Estimation Using Phase Features

• Published in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
• Main Authors: Ick, Christopher, Mehrabi, Adib, Jin, Wenyu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04-06-2023
• Subjects: Acoustic measurements; Estimation; Fingerprint recognition; Parameter estimation; Reverberation; Stability analysis; Time-frequency analysis
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP49357.2023.10094848

Modeling room acoustics in a real-world settings involves some degree of blind parameter estimation from noisy and reverberant audio. Modern approaches leverage convolutional neural networks (CNNs) in tandem with time-frequency representations. 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 phase-related features to extend recent approaches to blindly estimate the so-called "reverberation fingerprint" parameters, namely, volume and RT 60 . 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 phase features in both single-parameter and multi-parameter estimation strategies, using a task-specific dataset that consists of publicly available room impulse responses (RIRs), synthesized RIRs, and in-house measurements of real acoustic spaces.