• Corpus ID: 18758518

Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques

@article{Muda2010VoiceRA,
  title={Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques},
  author={Lindasalwa Muda and Mumtaj Begam and Irraivan Elamvazuthi},
  journal={ArXiv},
  year={2010},
  volume={abs/1003.4083}
}
Abstract — Digital processing of speech signal and voice recognition algorithm is very important for fast and accurate automatic voice recognition technology. [] Key Method Several methods such as Liner Predictive Predictive Coding (LPC), Hidden Markov Model (HMM), Artificial Neural Network (ANN) and etc are evaluated with a view to identify a straight forward and effective method for voice signal.

Figures and Tables from this paper

Fast Speaker Recognition using Efficient Feature Extraction Fast Speaker Recognition using Efficient Feature Extraction Fast Speaker Recognition using Efficient Feature Extraction Fast Speaker Recognition using Efficient Feature Extraction Technique
TLDR
This paper presents the viability of MFCC to extract features of speech signal and DTW to compare the corresponding test patterns and the non linear sequence alignment known as Dynamic Time Warping (DTW) is used as features matching technique.
Performance Analysis of Isolated Speech Recognition Technique Using MFCC and Cross-Correlation
TLDR
Mel Frequency Cepstral Coefficient technique has been used to process speech samples to attain the recognition and the recognition techniques show different percentages of accuracy.
Speech Recognition Using Euclidean Distance
TLDR
This paper describes an approach of speech recognition by using the Mel-Scale Frequency Cepstral Coefficient (MFCC) extracted from speech signal of spoken words.
Feature Extraction Using Mel Frequency Cepstrum Coefficients for Automatic Speech Recognition
TLDR
This paper presents MATLAB based feature extraction using Mel Frequency Cepstrum Coefficients (MFCC) for ASR and describes the development of an efficient speech recognition system using different techniques such as Mel frequency Cepstral Coefficient and Predictive Linear Coding.
Voice Recognition using Dynamic Time Warping and Mel-Frequency Cepstral Coefficients Algorithms
TLDR
This research aims to build a system for voice recognition using dynamic time wrapping algorithm, by comparing the voice signal of the speaker with pre-stored voice signals in the database, and extracting the main features of the Speaker voice signal using Mel-frequency cepstral coefficients, which is one of the most important factors in achieving high recognition accuracy.
Speaker Identification using MFCC and DTW Technique on the Enhanced Speech Signal in a Noisy Environment
TLDR
This work introduces a different technique which involves filtering the speech signal before extracting features from it, and it is found to be more efficient than the existing technique which uses MFCC alone for feature extraction.
Comparison of DTW and HMM for isolated word recognition
  • S. C. Sajjan, C. Vijaya
  • Computer Science
    International Conference on Pattern Recognition, Informatics and Medical Engineering (PRIME-2012)
  • 2012
This study proposes limited vocabulary isolated word recognition using Linear Predictive Coding(LPC) and Mel Frequency Cepstral Coefficients(MFCC) for feature extraction, Dynamic Time Warping(DTW)
Application of Mel Frequency Ceptrum Coefficients and Dynamic Time Warping For Developing an Isolated Speech Recognition System
TLDR
The recognition accuracy of speech recognition system has been a challenge due to insufficient combination of pre-processing techniques used for speech processing and this system was adopted with well supported pre- processing techniques to solve this problem.
Speech Recognition with Frequency Domain LineaR Prediction
  • P. Harshita, Akshay Adiga
  • Computer Science
    2018 International Conference on Communication and Signal Processing (ICCSP)
  • 2018
TLDR
The proposed feature vector with maximum accuracy is a combination of MFCC (Mel-Frequency Cepstral Coefficients) and FDLP (Frequency Domain Linear Prediction) after applying Short Time Energy (STE) to find the highest energy indexed block of 400 samples.
Speech Recognition Employing MFCC and Dynamic Time Warping Algorithm
  • M. Sood, Shruti Jain
  • Computer Science
    Innovations in Information and Communication Technologies (IICT-2020)
  • 2021
TLDR
In this paper, authors have worked upon the detection of a single user using multiple isolated words as speech signals using dynamic time warping (DTW) for feature extraction and feature matching.
...
...

References

SHOWING 1-10 OF 20 REFERENCES
Robust Computer Voice Recognition Using Improved MFCC Algorithm
  • Clarence Goh, Kok Leon
  • Computer Science
    2009 International Conference on New Trends in Information and Service Science
  • 2009
TLDR
A new MFCC algorithm that is capable of over 80% accuracy with less than 0.1ms CPU time taken for processing is explored, which could be used in security devices that use voice recognition technology for identification.
Malay language text-independent speaker verification using NN-MLP classifier with MFCC
TLDR
The applicability of Artificial Neural Network (ANNs) as core classifiers for Mel Frequency Cepstral Coefficients (MFCC) and a sampled method for speaker recognition that is based on ANNs are applied.
Dynamic programming algorithm optimization for spoken word recognition
TLDR
This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition, in which the warping function slope is restricted so as to improve discrimination between words in different categories.
From Dynamic Time Warping (DTW) to Hidden Markov Model (HMM) Final project report for ECE742 Stochastic Decision
TLDR
It is shown that DTW and stochastic DTW, HMM are actually sharing the same idea of DP (dynamic programming), and some experiments are performed to address this problem.
Word image matching using dynamic time warping
  • T. Rath, R. Manmatha
  • Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
TLDR
This work presents an algorithm for matching handwritten words in noisy historical documents that performs better and is faster than competing matching techniques and presents experimental results on two different data sets from the George Washington collection.
FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space
TLDR
This paper introduces FastDTW, an approximation of DTW that has a linear time and space complexity that uses a multilevel approach that recursively projects a solution from a coarse resolution and refines the projected solution.
Signal and Linear System Analysis
Preliminary Concepts: Signal and System Characteristics and Models Convolution Continuous-Time Signals and Systems Continuous Time Signals Continuous-Time Signal Spectra Time-Domain Analysis of
Dynamic Programming algorithm Optimization for spoken word Recognition, IEEE transaction on Acoustic speech and Signal Processing, Fecruary
  • 1978
Biomedical engineering labira‐ tory student pack
  • Biomedical engineering labira‐ tory student pack
...
...