Improved Window Function in the Application of MFCC Feature Parameter Extraction

2014 ◽  
Vol 556-562 ◽  
pp. 3703-3706
Author(s):  
Le Qiang Bai ◽  
Xue Wei Zhang
Keyword(s):  
Recognition Rate ◽  
Parameter Extraction ◽  
Side Lobe ◽  
Window Function ◽  
Main Lobe ◽  
Impact Function ◽  
Extraction Algorithm ◽  
Feature Parameter ◽  
Lobe Width ◽  
Kaiser Window

In view of spectrum leakage and the contradictory problem of spectrum accuracy of main lobe and reducing spectrum leakage, MFCC algorithm based on improved window function is proposed. Improved window function is based on the mathematical analysis of Kaiser window, and under the condition of finite sampling points minuses weighted impact function where is at the frequencies that side lobe peaks of correspond to. The amplitude of improved window compared with Kaiser window is smaller, and main lobe width is the same, solving the conflicting problem of main lobe width and side lobe amplitude and reducing spectrum leakage. The experimental results show that speech recognition rate of MFCC feature parameter extraction algorithm based on improved window function is better than Kaiser window and Hamming window.

FIR Filter Design Using Modified Lanczos Window Function

2012 ◽  
Vol 566 ◽  
pp. 49-56
Author(s):  
Md. Abdus Samad ◽  
Jia Uddin ◽  
Md. Razu Ahmed
Keyword(s):  
Filter Design ◽  
Side Lobe ◽  
Fir Filter ◽  
Window Function ◽  
Main Lobe ◽  
M 10 ◽  
Low Pass ◽  
Significant Performance ◽  
Fir Filter Design ◽  
Lobe Width

Attenuated side lobe peak in the range of around ~-45dB is required in many applications of signal processing and measurements. However, the problem is usual window based FIR filter design lies in its side lobes amplitudes that are higher than the requirement of application. We propose a modified Lanczos window function by heuristic by examining the Lanczos window, which has better performance like equiripple, minimum side lobe compared to the several commonly used windows. The proposed window has slightly larger main lobe width of the commonly used Hamming window, while featuring 5.1~18.5 dB smaller side lobe peak. The proposed modified Lanczos window maintains its maximum side lobe peak about -55.2~-51.9 dB compared to -39~-36.7 dB of Hamming window for M=10~14, while offering roughly equal main lobe width. Our simulated results also show significant performance upgrading of the proposed modified Lanczos window compared to the Kaiser, Gaussian, and Lanczos windows. The proposed modified Lanczos window also shows better performance than Dolph-Chebyshev window. Finally, the example of designed low pass FIR filter confirms the efficiency of the proposed modified Lanczos window.

Excitation series design and pulse compression synthesis for high-resolution Lamb wave inspection

2018 ◽  
Vol 18 (5-6) ◽  
pp. 1464-1478
Author(s):  
Jiadong Hua ◽  
Liang Zeng ◽  
Jing Lin ◽  
Liping Huang
Keyword(s):  
Lamb Wave ◽  
Pulse Compression ◽  
Lamb Waves ◽  
Dispersion Compensation ◽  
Synthesis Method ◽  
Side Lobe ◽  
Main Lobe ◽  
Window Functions ◽  
Windowing Technique ◽  
Lobe Width

Lamb wave pulse compression is a promising technique for ultrasonic nondestructive evaluation and structural health monitoring, in which the excitation waveform is designed to exhibit attractive auto-correlation characteristics including short main-lobe width and small side-lobe amplitude. However, narrowing main-lobe will increase side-lobe amplitude, and vice versa. Conventional time windowing technique is a balance between main-lobe width and side-lobe amplitude. An improvement over time windowing is proposed using pulse compression synthesis method. In this method, a series of excitation waveforms are used to actuate Lamb waves, each response is processed by pulse compression, and all the compression signals are summed together. The excitation series are constructed as linear chirps weighted with different combinations of rectangular and Hanning window functions. The selection of the combination coefficients is optimized to ensure best signal summation. The effectiveness of the proposed method is demonstrated by an experiment, and the robustness to inaccuracy in dispersion compensation is also evaluated. Application of the proposed method for damage detection is demonstrated by a further experiment.

Automatic Defect Extraction and Segmentation in Welding Seam Based on X-Ray Images

2011 ◽  
Vol 130-134 ◽  
pp. 2558-2562
Author(s):  
Ming Quan Wang ◽  
Yu Wang
Keyword(s):  
Mathematical Morphology ◽  
Parameter Extraction ◽  
Thin Wall ◽  
Edge Extraction ◽  
Welding Seam ◽  
X Ray ◽  
Extraction Algorithm ◽  
Feature Parameter ◽  
Defect Extraction ◽  
Enhancement Algorithm

In light of the characteristic of thin-wall weld joint in X-ray image, Flaw-edge extraction algorithm and image enhancement algorithm which is based on mathematical morphology are proposed in the study of flaw extraction technique. Therefore, the area of flaw and background can be removed successfully. On this basis, there are two algorithms to identify different flaw types: one is that spatial domain transform to extract flaw edge for clack, the other one is mathematical morphology which is combined with iteration threshold to extract flaw edge for pore; Experimental results show that both of algorithms can implement flaw extraction and segmentation automatically, which is lay a good foundation for flaw feature parameter extraction and recognition.

scholarly journals An Improved Feature Parameter Extraction Algorithm of Composite Detection Method Based on the Fusion Theory

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Zhou Ying ◽  
Jin Heli ◽  
Liu Banteng ◽  
Chen Yourong
Keyword(s):  
Eddy Current ◽  
Dispersion Model ◽  
Parameter Extraction ◽  
Quantitative Detection ◽  
Differential Signal ◽  
Feature Parameters ◽  
Pulsed Eddy Current ◽  
Extraction Algorithm ◽  
Feature Parameter ◽  
Subsurface Defects

An improved feature parameter extraction algorithm is proposed in this study to solve the problem of quantitative detection of subsurface defects. Firstly, the common feature parameters from the differential signal of pulsed eddy current and ultrasonic are extracted in time domain and frequency domain. Then, the dispersion model and ReliefF model are established to determine the weights of each parameter. Finally, the weights from the two different algorithms are fused by the D-S evidence theory to determine feature parameters. Compared with the PCA feature parameter algorithm from the pulsed eddy current or ultrasonic, the experiment results show the feature parameters extracted by the algorithm proposed in this paper are more effective in quantitative detection of subsurface defects. It will lead to high accuracy in the subsurface defections.

GESTURE RECOGNITION SYSTEM FOR NIGERIAN TRIBAL GREETING POSTURES USING SUPPORT VECTOR MACHINE

2020 ◽  
Vol 5 (2) ◽  
pp. 609
Author(s):  
Segun Aina ◽  
Kofoworola V. Sholesi ◽  
Aderonke R. Lawal ◽  
Samuel D. Okegbile ◽  
Adeniran I. Oluwaranti
Keyword(s):  
Support Vector Machine ◽  
Gesture Recognition ◽  
Recognition Rate ◽  
Recognition Task ◽  
Recognition System ◽  
Human Interaction ◽  
Support Vector ◽  
System A ◽  
Extraction Algorithm ◽  
Gaussian Blur

This paper presents the application of Gaussian blur filters and Support Vector Machine (SVM) techniques for greeting recognition among the Yoruba tribe of Nigeria. Existing efforts have considered different recognition gestures. However, tribal greeting postures or gestures recognition for the Nigerian geographical space has not been studied before. Some cultural gestures are not correctly identified by people of the same tribe, not to mention other people from different tribes, thereby posing a challenge of misinterpretation of meaning. Also, some cultural gestures are unknown to most people outside a tribe, which could also hinder human interaction; hence there is a need to automate the recognition of Nigerian tribal greeting gestures. This work hence develops a Gaussian Blur – SVM based system capable of recognizing the Yoruba tribe greeting postures for men and women. Videos of individuals performing various greeting gestures were collected and processed into image frames. The images were resized and a Gaussian blur filter was used to remove noise from them. This research used a moment-based feature extraction algorithm to extract shape features that were passed as input to SVM. SVM is exploited and trained to perform the greeting gesture recognition task to recognize two Nigerian tribe greeting postures. To confirm the robustness of the system, 20%, 25% and 30% of the dataset acquired from the preprocessed images were used to test the system. A recognition rate of 94% could be achieved when SVM is used, as shown by the result which invariably proves that the proposed method is efficient.

scholarly journals Handwritten tifinagh character recognition using simple geometric shapes and graphs

2019 ◽  
Vol 13 (2) ◽  
pp. 598
Author(s):  
Youssef Ouadid ◽  
Abderrahmane Elbalaoui ◽  
Mehdi Boutaounte ◽  
Mohamed Fakir ◽  
Brahim Minaoui
Keyword(s):  
Character Recognition ◽  
Graph Matching ◽  
Recognition Rate ◽  
Recognition System ◽  
Features Extraction ◽  
Experimental Results ◽  
Feature Points ◽  
Matching Method ◽  
Extraction Algorithm ◽  
Novel Algorithm

<p>In this paper, a graph based handwritten Tifinagh character recognition system is presented. In preprocessing Zhang Suen algorithm is enhanced. In features extraction, a novel key point extraction algorithm is presented. Images are then represented by adjacency matrices defining graphs where nodes represent feature points extracted by a novel algorithm. These graphs are classified using a graph matching method. Experimental results are obtained using two databases to test the effectiveness. The system shows good results in terms of recognition rate.</p>

scholarly journals Development and Analysis of New NLFM Waveform for Achieving Sidelobe Reduction and Narrowing of Main lobe Width

2021 ◽  
Vol 9 (7) ◽  
pp. 885-889
Keyword(s):  
Doppler Effect ◽  
Background Noise ◽  
Sampling Rate ◽  
Ambiguity Function ◽  
Main Lobe ◽  
The Doppler Effect ◽  
The Impact ◽  
Lobe Width

Aimed at narrowing main lobe width and reduced sidelobe values, we developed three new NLFM chirp waveforms. The ambiguity function and the impact of sampling rate and compression ratios of these waveforms are analyzed. Their performance is examined against the doppler effect and background noise. One of the three designed NLFM chirp waveforms is useful in applications requiring side lobes of -50 dB and narrow main lobe width. The new waveform could achieve reduced sidelobes and narrow main lobe width compared to LFM and other NLFM waveforms

scholarly journals Optimization of two-stage NLFM signal using Heuristic approach

2020 ◽  
Vol 13 (44) ◽  
pp. 4465-4473
Author(s):  
Chandu Kavitha ◽  
Keyword(s):  
Optimization Algorithm ◽  
Frequency Modulation ◽  
Pulse Compression ◽  
Piecewise Linear ◽  
Side Lobe ◽  
Linear Frequency Modulation ◽  
Main Lobe ◽  
Design And Optimization ◽  
Linear Frequency ◽  
Scripting Language

Background/Objectives: The design of appropriate Non-Linear Frequency Modulation (NLFM) signals continues to be the focus of research in radar pulse compression theory for sidelobe reduction. This study focuses on a heuristic design and optimization algorithm to optimize the side lobe values of the NLFM signal designed using two-piece wise linear frequency modulation (LFM) functions. Methods: 1) Heuristic search identifies the optimum B1, T1, and B2, T2, which yield the lowest sidelobe value of the designed function.2) Compute all the side lobe values of the designed NLFM signal using an algorithm developed in Python scripting language. To plot a complete contour map for all the calculated side lobe values, which helps identify the associated variations in the range of side lobe values. Finally, optimize the side lobe values keeping the main lobe width and time-bandwidth (BT) product unchanged by designing a dynamic optimization algorithm. Findings: The algorithm developed considered all side lobe levels after the main lobe for optimization. The focus is mainly on the peak sidelobe ratio (PSLR) value without affecting the other parameters. The results demonstrate that the achieved side lobes exhibit their desired levels. Novelty: The method is useful in all types of hardware associated with weather radar applications to military solutions. The technique can be extended to other multistage signals consisting of piecewise linear Segments. Keywords: Contour; LFM; NLFM; optimization; PSLR

Sign in / Sign up

Export Citation Format

Share Document