Speech bottleneck feature extraction method based on overlapping group lasso sparse deep neural network

2018 ◽  
Vol 99 ◽  
pp. 56-61 ◽  
Author(s):  
Yuan Luo ◽  
Yu Liu ◽  
Yi Zhang ◽  
Congcong Yue
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Deep Neural Network ◽  
Group Lasso ◽  
Feature Extraction Method

scholarly journals A Wavelet Scattering Feature Extraction Approach for Deep Neural Network Based Indoor Fingerprinting Localization

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1790 ◽  
Author(s):  
Bedionita Soro ◽  
Chaewoo Lee
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Deep Neural Network ◽  
Small Deformation ◽  
Rotation Invariant ◽  
Feature Extraction Method ◽  
Path Coefficients ◽  
Scattering Transform ◽  
Artificial Neural Network Ann

The performance of an Artificial Neural Network (ANN)-based algorithm is subject to the way the feature data is extracted. This is a common issue when applying the ANN to indoor fingerprinting-based localization where the signal is unstable. To date, there is not adequate feature extraction method that can significantly mitigate the influence of the receiver signal strength indicator (RSSI) variation that degrades the performance of the ANN-based indoor fingerprinting algorithm. In this work, a wavelet scattering transform is used to extract reliable features that are stable to small deformation and rotation invariant. The extracted features are used by a deep neural network (DNN) model to predict the location. The zeroth and the first layer of decomposition coefficients were used as features data by concatenating different scattering path coefficients. The proposed algorithm has been validated on real measurements and has achieved good performance. The experimentation results demonstrate that the proposed feature extraction method is stable to the RSSI variation.

scholarly journals Deteksi Api Pada Video Menggunakan Metode Artificial Neural Network

2021 ◽  
Vol 3 (1) ◽  
pp. 96-107
Author(s):  
Budiman Rabbani
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Gray Level ◽  
Backpropagation Neural Network ◽  
Validation Process ◽  
Feature Extraction Method ◽  
Time Value ◽  
Occurrence Matrix

Abstract The camera is one of the tools used to collect images. Cameras are often used for the safety of homes, highways and others. Then in this study camera captures are used to support fire objects because fire is one of the causes of safety that can be controlled. Therefore, by utilizing a capture camera will see the best model of backpropagation neural network by combining the local binary patern (LBP) feature extraction method and the Gray Level Co-occurrence Matrix (GLCM) to access the fire. Then to evaluate the performance of the model created using three parameters that contain accuracy, recall, precision. The data in this study consisted of videos with variations of fire and non-fire videos. Based on the final results of the study, accuracy, remember, the best precision obtained simultaneously 96%, 97%, 97%. Then the validation process was done using 30 videos with a variation of 15 fire videos and 15 non-fire videos and obtained an accuracy of 86.6% with an average time value of 6.029 minutes.

Speaker and Speech Recognition using Deep Neural Network

2018 ◽  
Vol 6 (8) ◽  
pp. 118 ◽  
Author(s):  
Gurpreet Kaur ◽  
Mohit Srivastava ◽  
Amod Kumar
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Feature Extraction ◽  
Speech Recognition ◽  
Deep Neural Network ◽  
Rate Sensitivity ◽  
Extraction Process ◽  
Recall Rate ◽  
Feature Extraction Method ◽  
Work Model

In command and control applications, feature extraction process is very important for good accuracy and less learning time. In order to deal with these metrics, we have proposed an automated combined speaker and speech recognition technique. In this paper five isolated words are recorded with four speakers, two males and two females. We have used the Mel Frequency Cepstral Coefficient (MFCC)  feature extraction method with Genetic Algorithm to optimize the extracted features and generate an appropriate feature set. In first phase, feature extraction using MFCC is executed following the feature optimization using Genetic Algorithm and in last & third phase, training is conducted using the Deep Neural Network. In the end, evaluation and validation of the proposed work model is done by setting real environment. To check the efficiency of the proposed work, we have calculated the parameters like accuracy, precision rate, recall rate, sensitivity and specificity..

Sign in / Sign up

Export Citation Format

Share Document