A NOVEL SPEECH ENHANCEMENT APPROACH BASED ON MODIFIED DCT AND IMPROVED PITCH SYNCHRONOUS ANALYSIS

Abstract

Speech enhancement has become an essential issue within the field of speech and signal processing, because of the necessity to enhance the performance of voice communication systems in noisy environment. There has been a number of research works being carried out in speech processing but still there is always room for improvement. The main aim is to enhance the apparent quality of the speech and to improve the intelligibility. Signal representation and enhancement in cosine transformation is observed to provide significant results. Discrete Cosine Transformation has been widely used for speech enhancement. In this research work, instead of DCT, Advanced DCT (ADCT) which simultaneous offers energy compaction along with critical sampling and flexible window switching. In order to deal with the issue of frame to frame deviations of the Cosine Transformations, ADCT is integrated with Pitch Synchronous Analysis (PSA). Moreover, in order to improve the noise minimization performance of the system, Improved Iterative Wiener Filtering approach called Constrained Iterative Wiener Filtering (CIWF) is used in this approach. Thus, a novel ADCT based speech enhancement using improved iterative filtering algorithm integrated with PSA is used in this approach.