Aurora-2 Database Research Articles

Feature Compensation Based on Soft Decision

In this letter, we propose a novel approach to feature compensation for robust speech recognition in noisy environments. Our approach combines the interacting multiple model (IMM) and spectral subtraction (SS) techniques based on a soft decision for speech presence. The proposed approach shows 13.56% of average relative improvement compared to the IMM algorithm in the speech recognition experiments performed on the AURORA2 database when clean condition training is applied.