Paper Title
Modified DCT Based Speech Enhancement In Vehicular Environments

Abstract
Speech enhancement aims to improve speech quality by using various algorithms. The objective of speech enhancement is improvement in intelligibility and or overall perceptual quality of speech signal using various signal processing techniques. Enhancing of speech corrupted by noise, or noise reduction, is an important field of speech enhancement, and used in many applications such as mobile phones, Voice Over Internet Protocol (VoIP), teleconferencing systems, speech recognition systems, and hearing aids. Our aim is to reduce the background noise (such as car, train noise, etc.) in applications as mentioned above. In our approach, we make use of Discrete Cosine Transform (DCT) in which we exploit the "energy compaction" property of DCT, which is the ability to pack the energy of the data sequence into as few frequency coefficients as possible. This method is expected to produce speech with greater intelligibility and lower noise levels and the effectiveness will be validated using qualitative and quantitative measures. Keywords- Discrete Cosine Transform; Spectral Subtraction; Energy Compaction; Itakura-Saito Distance; lp Spectrum