No abstract

This paper presents a novel method of classifying speech phonemes. Four hybrid techniques based on the acousticphonetic approach and pattern recognition approach are used to emphasize the principle idea of this research. The first hybrid model is constructed of fixed state, structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network, Vector Quantization (FS-HMM-GM-MBTI-CNN-VQ). The second hybrid model is constructed of variable state, dynamically structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network, Vector Quantization (VS-HMM-GM-MBTI-CNN-VQ). The third hybrid model is constructed of fixed state, structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network (FS-HMM-GM-MBTI-CNN). The fourth hybrid model is constructed of variable state, dynamically structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network (VS-HMM-GM-MBTI-CNN). TIMIT database is used in this paper. All phones are classified into five classes and segregated into Vowels, Plosives, Fricatives, Nasals, and Silences. The results show that using (VS-HMM-GM-MBTI-CNN-VQ) is an available method for classification of phonemes, with the potential for use in applications such as automatic speech recognition and automatic language identification. Competitive results are achieved especially in nasals, plosives, and silence high successive rates than others.

Controlling a quadcopter is a challenging task because of the inherent high nonlinearity of a quadcopter system. In this paper, a new quaternion-based nonlinear feedback controller for attitude and altitude regulation of a quadcopter is proposed. The dynamic model of the quadcopter is derived using Newton and Euler equations. The proposed controller is established based on a feedback linearization technique to control and regulate the quadcopter. Global asymptotic stability of the designed controller is verified using Lyapunov stability criterion. A comparison between the proposed controller and two states of the art quadcopter controller is performed to evaluate its efficiency and performance. The efficiency of the proposed controller is clearly shown when the quadcopter is in or near a critical position. Simulations are performed to assess the transient and steady state performance. Steady state error and Max error indicators demonstrate the validity and effectiveness of the proposed algorithm with different reference controllers.

Non-Perspective Three Point Pose (NP3P) problem is a generalization of the classical three point pose problem for the case of multi-camera that have no common projection center. In this paper, we develop a simple, minimal algebraic solution to the NP3P problem where the projection rays of three points may have arbitrary but known directions. This problem is known to have a maximum of eight solutions. The problem is formulated mathematically as the solution of three multivariate polynomials. The technique of Sylvester matrix resultants of two equations is used to obtain an eighth order polynomial that can be solved to yield the pose parameters. The accuracy and computational cost of the new method is compared to other methods reported in the literature and it was found to have comparable accuracy with less computational cost.Index Terms-Camera pose estimation, perspective n point problem (PnP), non-perspective n point problem (NPnP), computer vision.

No abstract