Direct-to-Reverberant Ratio Estimation on the ACE Corpus Using a Two-channel Beamformer
This work addresses room acoustic characterization for audio processing applications, but it is incremental as it applies an existing method to new data.
The paper evaluated the DENBE algorithm for Direct-to-Reverberant Ratio estimation on the ACE corpus with measured impulse responses and noise, finding that it outperformed baselines across all SNRs and noise types, and demonstrated estimation in frequency bands.
Direct-to-Reverberant Ratio (DRR) is an important measure for characterizing the properties of a room. The recently proposed DRR Estimation using a Null-Steered Beamformer (DENBE) algorithm was originally tested on simulated data where noise was artificially added to the speech after convolution with impulse responses simulated using the image-source method. This paper evaluates the performance of this algorithm on speech convolved with measured impulse responses and noise using the Acoustic Characterization of Environments (ACE) Evaluation corpus. The fullband DRR estimation performance of the DENBE algorithm exceeds that of the baselines in all Signal-to-Noise Ratios (SNRs) and noise types. In addition, estimation of the DRR in one third-octave ISO frequency bands is demonstrated.