Lombard speech model for automatic enhancement of speech intelligibility over telephone channel

This paper aims at evaluating the performance of a “Lombard effect model” for improving speech intelligibility over telephone channel. It is well known that the naturalness and intelligibility of speech degrades rapidly in communication channels, such as phone networks or public address systems. To reduce the degradation, a ”Lombard effect mimicking” system has been proposed to modify the variations of duration, formant frequencies, formant bandwidth, pitch and energy in each frequency band of normal speech for compensating Lombard effect. In order to validate the effectiveness of our Lombard effect mimicking system for speech intelligibility improvement, we evaluated synthetic Lombard speech over telephone channel. From subjective listening test, it is shown that the proposed compensation algorithm increases the intelligibility of speech in telephone channel environments at 5 dB Signal-to-Noise ratio (SNR) and 10 dB SNR by nearly 10% and 13.9% over the unprocessed signals respectively.