Analyzing Mel Frequency Cepstral Coefficient for Recognition of Isolated English Word using DTW Matching

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

Incorporating Human Behavioral Patterns in Big Data Text Analytics

One of the modern day emerging technologies include Big Data Analysis. Big Data refers to the huge terabytes of data being collected on internet web sites such as Facebook, Twitter etc, Machine data such as sensors an...

Survey Paper on Music Beat Tracking

Tempo in music is beats perceived by us in unit time. The tempo is measured as number of beats per minute (BPM) in a music clip. This paper includes two algorithms used to measure tempo of music file. First one is an...

Effective Routing Plan For Quality Results On Linked Data Using Keyword Search

Keyword search is a natural world view for seeking connected information sources on the web. We propose to route keywords just to pertinent sources to reduce the high cost of handling keyword search queries over all...

An Efficient Parallel Processing Technique For Large Text Files

Now a days the data was increasing rapidly because of heterogeneous resources. The data that is useful for large organisations will required large number of computing resources for processing large data sets. there a...

Design of Parallel MAC Based On Radix-4 & Radix-8 Modified Booth Algorithm

This paper focused on a combined process of multiplication and accumulation based on radix-4 & radix-8 booth encodings. In this Paper, we investigate the method of implementing the Parallel MAC with the smallest possi...

Download PDF file
  • EP ID EP27897
  • DOI -
  • Views 209
  • Downloads 0

How To Cite

Mr. Nitin Goyal, Dr. R. K. Purwar (2014). Analyzing Mel Frequency Cepstral Coefficient for Recognition of Isolated English Word using DTW Matching. International Journal of Research in Computer and Communication Technology, 3(4), -. https://europub.co.uk/articles/-A-27897