An improved spectral subtraction algorithm based on auditory masking in voice human-computer interaction

As the primary research area of the Multimoda1 Human-computer Interaction, Voice Interaction mainly involves extraction and identification of the natural speech signal, where the former provides the reliable signal sources, which are analyzed by the latter. The speech enhancement technology is studied in this paper, aiming at the Voice Interactive. We propose an improved spectral subtraction (SS) algorithm based on auditory masking effect. The simulated results compared to the traditional SS show the effectiveness and superiority of the improved algorithm.