Abstract

In today's world, to make man-machine interaction more effective speech recognition plays an important role in speech processing. This paper presents the application of Hilbert-Huang transform (HHT), a mathematical tool applied for feature extraction phase of the speech signal processing. These features are modeled and evaluated using Vector Quantization(VQ) and Fuzzy C Means(FCM) techniques. The proposed system highlights the importance of Discrete Cosine Transformation(DCT) applied for Hilbert Huang Transform to extract the better speech signal parameters. The features obtained from this process has better recognition accuracies. It also demonstrates the efficiency of DCT with HHT for FCM clustering technique over the VQ technique. The performance of HHT- FCM is discussed with the termination criteria ‘e’ and fuzzifier ‘m’ parameters of FCM.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call