Performance estimation of reverberant speech recognition based on reverberant criteria RSR-dn with acoustic parameters

Reverberation-robust speech recognition has become very important in the field of distant-talking speech recognition. However, as no common reverberation criteria for the recognition of reverberant speech have yet been proposed, it has been difficult to estimate its effectiveness. To address this problem in 2007, we investigated early and late reflections on distanttalking speech recognition to help define suitable reverberation criteria. We here propose new reverberation criteria RSR-Dn (Reverberant Speech Recognition criteria with Dn) based on our previous investigations and ISO3382 acoustic parameters. We first designed the criteria using the relationship between speech recognition performance and ISO3382 acoustic parameters. We then estimated the speech recognition performance obtained with the criteria. Evaluation experiments confirmed that the recognition performance can be accurately and robustly estimated with our proposed reverberation criterion RSRD20Q (Reverberant Speech Recognition criterion withD20 and Quadratic regression function).