scholarly journals SPEAKER IDENTIFICATION MODEL BASED ON DEEP NURAL NETWOKS

2022 ◽  
pp. 108-114
Author(s):  
Saadaldeen Rashid Ahmed ◽  
Zainab Ali Abbood ◽  
hameed Mutlag Farhan ◽  
Baraa Taha Yasen ◽  
Mohammed Rashid Ahmed ◽  
...  
Keyword(s):  
Deep Neural Network ◽  
Reference Model ◽  
Speaker Identification ◽  
Space Station ◽  
Activation Functions ◽  
Data Framework ◽  
Machine Learning Applications ◽  
Small Footprint ◽  
The Cost ◽  
Identification Model

This study aims is to establish a small system of text-independent recognition of speakers for a relatively small group of speakers at a sound stage. The fascinating justification for the International Space Station (ISS) to detect if the astronauts are speaking at a specific time has influenced the difficulty. In this work, we employed Machine Learning Applications. Accordingly, we used the Direct Deep Neural Network (DNN)-based approach, in which the posterior opportunities of the output layer are utilized to determine the speaker’s presence. In line with the small footprint design objective, a simple DNN model with only sufficient hidden units or sufficient hidden units per layer was designed, thereby reducing the cost of parameters through intentional preparation to avoid the normal overfitting problem and optimize the algorithmic aspects, such as context-based training, activation functions, validation, and learning rate. Two commercially available databases, namely, TIMIT clean speech and HTIMIT multihandset communication database and TIMIT noise-added data framework, were tested for this reference model that we developed using four sound categories at three distinct signal-to-noise ratios. Briefly, we used a dynamic pruning method in which the conditions of all layers are simultaneously pruned, and the pruning mechanism is reassigned. The usefulness of this approach was evaluated on all the above contact databases

scholarly journals Smooth input preparation for quantum and quantum-inspired machine learning

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Zhikuan Zhao ◽  
Jack K. Fitzsimons ◽  
Patrick Rebentrost ◽  
Vedran Dunjko ◽  
Joseph F. Fitzsimons
Keyword(s):  
Machine Learning ◽  
Quantum Algorithms ◽  
Machine Learning Algorithms ◽  
Low Rank ◽  
Smoothed Analysis ◽  
Machine Learning Applications ◽  
Data Points ◽  
Input Model ◽  
The Cost ◽  
Input Perturbation

AbstractMachine learning has recently emerged as a fruitful area for finding potential quantum computational advantage. Many of the quantum-enhanced machine learning algorithms critically hinge upon the ability to efficiently produce states proportional to high-dimensional data points stored in a quantum accessible memory. Even given query access to exponentially many entries stored in a database, the construction of which is considered a one-off overhead, it has been argued that the cost of preparing such amplitude-encoded states may offset any exponential quantum advantage. Here we prove using smoothed analysis that if the data analysis algorithm is robust against small entry-wise input perturbation, state preparation can always be achieved with constant queries. This criterion is typically satisfied in realistic machine learning applications, where input data is subjective to moderate noise. Our results are equally applicable to the recent seminal progress in quantum-inspired algorithms, where specially constructed databases suffice for polylogarithmic classical algorithm in low-rank cases. The consequence of our finding is that for the purpose of practical machine learning, polylogarithmic processing time is possible under a general and flexible input model with quantum algorithms or quantum-inspired classical algorithms in the low-rank cases.

scholarly journals An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network

2021 ◽  
Author(s):  
Anh Nguyen ◽  
Khoa Pham ◽  
Dat Ngo ◽  
Thanh Ngo ◽  
Lam Pham
Keyword(s):  
Neural Network ◽  
Supervised Classification ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Network Architectures ◽  
Activation Functions ◽  
Scene Classification ◽  
Learning Network ◽  
Deep Learning Network

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions.Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.

scholarly journals Shuttle diplomacy

2011 ◽  
Vol 133 (07) ◽  
pp. 46-53
Author(s):  
Burton Dicht
Keyword(s):  
International Space Station ◽  
Space Shuttle ◽  
Space Exploration ◽  
Space Station ◽  
Operating Costs ◽  
Space Program ◽  
International Space ◽  
New Vision ◽  
The Cost ◽  
The U.S

This article analyzes the decisions and technological challenges that drove the Space Shuttle’s development. The goal of the Shuttle program was to create a reusable vehicle that could reduce the cost of delivering humans and large payloads into space. Although the Shuttle was a remarkable flying machine, it never lived up to the goals of an airline-style operation with low operating costs. In January 2004, a year after the Columbia accident, President George W. Bush unveiled the “Vision for U.S. Space Exploration” to guide the U.S. space effort for the next two decades. A major component of the new vision, driven by the recommendations of the Columbia Accident Investigation Board, was to retire the Space Shuttle fleet as soon as the International Space Station assembly was completed. With cancellation of the Constellation program in 2010, the planned successor to the Shuttle, the U.S. space program is now in an era of uncertainty.

The Research on Permanent Magnetic Synchronous Motor Vector Control Based on MRAS

2015 ◽  
Vol 719-720 ◽  
pp. 381-387
Author(s):  
Bo Ze Zhang ◽  
Yi Ruan
Keyword(s):  
Vector Control ◽  
Control Strategy ◽  
Reference Model ◽  
Synchronous Motor ◽  
Position Sensor ◽  
Sensorless Vector Control ◽  
The Cost ◽  
Motor Drive System ◽  
The Mathematical Model ◽  
Additional Space

The precise speed and torque controls of Permanent Magnetic Synchronous Motor (PMSM) are usually realized by using speed or position sensor. However, the mounting of speed or position sensor requires an additional space. The cost of motor drive system with speed or position sensor is high, the reliability is low and is difficult to maintain. This paper presents one novel control strategy for PMSM sensorless vector control based on model reference adaption system(MRAS). This control strategy doesn’t need any speed or position sensor and can estimate the rotor speed with a few parameters. In this paper, PMSM itself is selected as reference model, and the mathematical model of PMSM which includes estimated parameter is regarded as adjustable model. The output error of these two models is used to drive the adaption mechanism and the estimated speed is obtained. The simulation results verify the proposed control strategy is effective, it has excellent dynamic and stable responses, the estimated speed precision is high and the system is robust.

CTL-DNNet: Effective Circular Traffic Light Recognition with a Deep Neural Network

2017 ◽  
Vol 31 (11) ◽  
pp. 1750037 ◽  
Author(s):  
Di Wang ◽  
Hong Bao ◽  
Feifei Zhang
Keyword(s):  
Neural Network ◽  
Autonomous Vehicles ◽  
Deep Neural Network ◽  
Road Traffic ◽  
High Accuracy ◽  
Activation Functions ◽  
Traffic Light ◽  
Traffic Lights ◽  
Learning Network ◽  
Deep Learning Network

This paper proposed an algorithm for a deep learning network for identifying circular traffic lights (CTL-DNNet). The sample labeling process uses translation to increase the number of positive samples, and the similarity is calculated to reduce the number of negative samples, thereby reducing overfitting. We use a dataset of approximately 370[Formula: see text]000 samples, with approximately 20[Formula: see text]000 positive samples and approximately 350[Formula: see text]000 negative samples. The datasets are generated from images taken at the Beijing Garden Expo. To obtain a very robust method for the detection of traffic lights, we use different layers, different cost functions and different activation functions of the depth neural network for training and comparison. Our algorithm has evaluated autonomous vehicles in varying illumination and gets the result with high accuracy and robustness. The experimental results show that CTL-DNNet is effective at recognizing road traffic lights in the Beijing Garden Expo area.

scholarly journals Text-Independent Speaker Identification Through Feature Fusion and Deep Neural Network

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 32187-32202 ◽  
Author(s):  
Rashid Jahangir ◽  
Ying Wah TEh ◽  
Nisar Ahmed Memon ◽  
Ghulam Mujtaba ◽  
Mahdi Zareei ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Feature Fusion ◽  
Speaker Identification
Sign in / Sign up

Export Citation Format

Share Document