ON INTELLIGIBILITY ASSESSMENT OF IDEAL BINARY-MASKED NOISY SPEECH WITH ACCEPTANCE OF ROOM ACOUSTIC

Vladimír Sedlák – Daniela Ďuračková – Roman Záluský – Tomáš Kováčik

   In this paper the intelligibility of ideal binary-masked noisy signal is evaluated for different signal to noise ratio (SNR), mask error, masker types, distance between source and receiver, reverberation time and local criteria for forming the binary mask. The ideal binary mask is computed from time-frequency decompositions of target and masker signals by thresholding the local SNR within time-frequency units. The intelligibility of separated signal is measured using different objective measures computed in frequency and perceptual domain. The present study replicates and extends the findings which were already presented but mainly shows impact of room acoustic on the intelligibility performance of IBM technique.

Keywords: ideal binary mask, speech separation, intelligibility, room acoustic

[full-paper]