Blind Estimation of Speech Transmission Index and Room Acoustic Parameters by Using Extended Model of Room Impulse Response Derived From Speech Signals

The speech transmission index (STI) and room acoustic parameters (RAPs) are essential metrics for assessing quality predicting listening difficulty in a sound field. Although STI important RAPs, such as reverberation time clarity, can be derived from the impulse response (RIR), measuring RIR regularly occupied spaces is difficult. Hence, simultaneous blind estimation of RAPs an imperative challenge issue that must addressed. However, most existing methods provide only single parameter require massive dataset model training. A deterministic method presented blindly estimating five using stochastic approximates unknown RIR. An algorithm formulated uses temporal power envelope reverberant signal to determine optimal model. mathematical dereverabation process was proposed based on signals. This maps observed signal. estimated then synthesized estimate RAPs. simulation conducted evaluate signals, comparison best previous work. root-mean-square error (RMSE) Pearson correlation coefficient between measured values were used evaluation metrics. In terms STI, achieves accuracy with RMSE 0.037. With regard other remains consistent works. results show effectively simultaneously without any