Detecting relevant acoustic events for piloting improvement of intelligibility

This paper presents a speech signal transformation which slows down speech signals selectively and enhances some important acoustic cues. This transformation can be used for hearing aids and also for second language acquisition by facilitating oral comprehension. Selective slowing down relies on the use the TD-PSOLA synthesis method. The strategy used to control slowing down exploits a spectral variation function which locates rapid spectral changes. The enhancement simply consists of amplifying stop bursts and unvoiced fricatives. These acoustic cues are detected automatically through the examination of energy criteria. This approach was evaluated in the context of second language acquisition, more precisely by evaluating improvements in oral comprehension through the transformation, the detection and a perceptive experiment. The detection of relevant events gives good results and experiments show that the oral comprehension is improved.