SRMR variants for improved blind room acoustics characterization
This work addresses the challenge of improving speech recognition and enhancement in reverberant environments for applications like audio processing, but it is incremental as it builds on existing SRMR-based methods.
The paper tackled the problem of blind estimation of room acoustics metrics like reverberation time (RT) and direct-to-reverberant energy ratio (DRR) from speech signals, showing that variants of the SRMR measure outperform a state-of-the-art baseline with a 23% relative improvement in RMSE and up to 47% relative improvement in correlation for RT prediction.
Reverberation, especially in large rooms, severely degrades speech recognition performance and speech intelligibility. Since direct measurement of room characteristics is usually not possible, blind estimation of reverberation-related metrics such as the reverberation time (RT) and the direct-to-reverberant energy ratio (DRR) can be valuable information to speech recognition and enhancement algorithms operating in enclosed environments. The objective of this work is to evaluate the performance of five variants of blind RT and DRR estimators based on a modulation spectrum representation of reverberant speech with single- and multi-channel speech data. These models are all based on variants of the so-called Speech-to-Reverberation Modulation Energy Ratio (SRMR). We show that these measures outperform a state-of-the-art baseline based on maximum-likelihood estimation of sound decay rates in terms of root-mean square error (RMSE), as well as Pearson correlation. Compared to the baseline, the best proposed measure, called NSRMR_k , achieves a 23% relative improvement in terms of RMSE and allows for relative correlation improvements ranging from 13% to 47% for RT prediction.