Analyzing Mel Frequency Cepstral Coefficient for Recognition of Isolated English Word using DTW Matching
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2014, Vol 3, Issue 4
Abstract
In this paper we proposed Mel-frequency cepstrum coefficients feature extraction and Dynamic Time Warping matching algorithm for speech recognition. Feature vector (Mel-frequency cepstrum coefficients) obtained from speech frame by using Fast Fourier Transform and Discrete Cosine Transform. DTW matching algorithm was applied on feature vector thus obtained by varying number of MFCC coefficients. Clustered database was prepared for template matching. The effectiveness of varying vector size over matching was considered.
Authors and Affiliations
Mr. Nitin Goyal , Dr. R. K. Purwar
Keywords
Related Articles
- EP ID EP27897
- DOI -
- Views 240
- Downloads 0
Echo Noise Reduction Using Dynamic Selection Of Sub Band Adaptive Filters
Versatile filters assume a paramount part clinched alongside advanced day sign transforming with provisions for example, such that commotion cancellation, sign prediction, versatile reaction cancellated What's more r...
A Novel Secure On-Demand Routing Protocol for MANET using RSA Triple Key Technique
MANET (Mobile and Ad hoc Networks) are networks in which nodes are mobile and link connectivity might change all the time. In this kind of networks routing, security and key management are the important and complex p...
A Systematic Approach For Testing And Debugging Networks Called Atpg
ATPG recognize router configurations and produces a device-independent model. The imitation is used to make a minimum set of test packets to simply put into effect every link in the network or maximally exercise ever...
Effective Mining Scheme for Large Streams Personalized Data Using Sparse Data
Reference methods are extremely significant in the fields of E-commerce and other Web-based services. One of the major complexities is dynamically providing high-quality suggestion on sparse data. In this paper a wor...
Logo Matching And Recognition System Using Surf
Matching is an important part of a model based object recognition system. Matching is a difficult task because images do not present perfect data, noise and occlusions greatly complicate the task. Although no existin...