Application of multimedia network english listening model based on confidence learning algorithm for speech recognition

2021 ◽  
Author(s):  
Yingting Zhang ◽  
Zewei Huang
Keyword(s):  
Speech Recognition ◽  
Learning Algorithm ◽  
Model Based ◽  
Multimedia Network

A multimedia network English listening teaching model based on confidence learning algorithm of speech recognition

2021 ◽  
pp. 002072092098467
Author(s):  
Yubing Yao ◽  
Congying Ma
Keyword(s):  
Speech Recognition ◽  
Posterior Probability ◽  
Learning Algorithm ◽  
Confidence Score ◽  
Posteriori Probability ◽  
Support Vector ◽  
Teaching Model ◽  
Network Technology ◽  
Model Based ◽  
Multimedia Network

Language is the most important communication tool of human beings, and listening is one of the basic skills of language expression. Without good listening comprehension ability, it is impossible to use language flexibly to communicate. Due to the influence of traditional education mode, Chinese students' English listening is generally poor. Therefore, a new English listening teaching mode is needed to help students improve their English listening. In this paper, multimedia network technology is used to realize the integrated English listening teaching of listening, speaking and dictation skills, and a multimedia network English listening teaching model based on speech recognition confidence learning algorithm is proposed. In order to improve the effectiveness of the mainstream confidence method based on Lattice posterior probability, this paper proposes an improved confidence algorithm based on Lattice posterior probability, and then converts the obtained confidence score into discriminant confidence score by Support Vector Machine(SVM) to further enhance the discriminant ability of confidence. Aiming at the imbalance of training data, a score correction strategy is proposed. The experiment shows that the English listening teaching model realized by using multimedia network technology can effectively enhance the students interest in learning and improve their listening ability. And the improvement of the mainstream confidence method based on Lattice posteriori probability can effectively improve the recognition ability of the algorithm and further improve the students’ English listening learning effect.

scholarly journals Multimedia Network English Reading Teaching Model Based on Speech Recognition Confidence Learning Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-9 ◽  
Author(s):  
Chuanju Wang
Keyword(s):  
Speech Recognition ◽  
Learning Algorithm ◽  
Principal Component ◽  
Learning System ◽  
Svm Classifier ◽  
Communication Tool ◽  
English Teaching ◽  
English Reading ◽  
Multimedia Network ◽  
Reading Teaching

With deepening internationalization, English has become an increasingly important communication tool. Because traditional English teaching has short teacher-student interaction time, lack of oral English training environment, and single learning method, the oral English teaching is not ideal, and the students’ “speaking” confidence is insufficient. Aimed at addressing the exposed problems of traditional English reading teaching, this paper proposes a multimedia-based English reading teaching mode. On this basis, establish a voice recognition phoneme network grid to detect the recognition results. Secondly, the lattice is used to generate the confusion network mesh, and the acoustic posterior probability is calculated. Then, the feature vector is input into the SVM classifier for confidence mark, and finally the feature is extracted by principal component analysis. The research shows that multimedia network teaching can teach more vividly, increasing the initiative of students. At the same time, it is shown that the speech recognition confidence learning algorithm can improve the language learning system.

scholarly journals NLM-HS: Navigation Learning Model Based on a Hippocampal–Striatal Circuit for Explaining Navigation Mechanisms in Animal Brains

2021 ◽  
Vol 11 (6) ◽  
pp. 803
Author(s):  
Jie Chai ◽  
Xiaogang Ruan ◽  
Jing Huang
Keyword(s):  
Prefrontal Cortex ◽  
Learning Algorithm ◽  
Learning Model ◽  
Cognitive Map ◽  
Model Based ◽  
Animal Navigation ◽  
Environmental Cognition ◽  
Neurophysiological Studies ◽  
Planning Algorithm ◽  
Two Stages

Neurophysiological studies have shown that the hippocampus, striatum, and prefrontal cortex play different roles in animal navigation, but it is still less clear how these structures work together. In this paper, we establish a navigation learning model based on the hippocampal–striatal circuit (NLM-HS), which provides a possible explanation for the navigation mechanism in the animal brain. The hippocampal model generates a cognitive map of the environment and performs goal-directed navigation by using a place cell sequence planning algorithm. The striatal model performs reward-related habitual navigation by using the classic temporal difference learning algorithm. Since the two models may produce inconsistent behavioral decisions, the prefrontal cortex model chooses the most appropriate strategies by using a strategy arbitration mechanism. The cognitive and learning mechanism of the NLM-HS works in two stages of exploration and navigation. First, the agent uses a hippocampal model to construct the cognitive map of the unknown environment. Then, the agent uses the strategy arbitration mechanism in the prefrontal cortex model to directly decide which strategy to choose. To test the validity of the NLM-HS, the classical Tolman detour experiment was reproduced. The results show that the NLM-HS not only makes agents show environmental cognition and navigation behavior similar to animals, but also makes behavioral decisions faster and achieves better adaptivity than hippocampal or striatal models alone.

Roboterbasierte spanende Bearbeitung*/Robot-Based Milling Operation. Machine Learning Algorithm for a model-based feed-forward torque control

2019 ◽  
Vol 109 (05) ◽  
pp. 352-357
Author(s):  
C. Brecher ◽  
L. Gründel ◽  
L. Lienenlüke ◽  
S. Storms
Keyword(s):  
Machine Learning ◽  
Position Control ◽  
Learning Algorithm ◽  
Milling Process ◽  
Industrial Robots ◽  
Torque Control ◽  
Feed Forward ◽  
Control Loops ◽  
Model Based ◽  
Machine Learning Approach

Die Lageregelung von konventionellen Industrierobotern ist nicht auf den dynamischen Fräsprozess ausgelegt. Eine Möglichkeit, das Verhalten der Regelkreise zu optimieren, ist eine modellbasierte Momentenvorsteuerung, welche in dieser Arbeit aufgrund vieler Vorteile durch einen Machine-Learning-Ansatz erweitert wird. Hierzu wird die Umsetzung in Matlab und die simulative Evaluation erläutert, die im Anschluss das Potenzial dieses Konzeptes bestätigt.   The position control of conventional industrial robots is not designed for the dynamic milling process. One possibility to optimize the behavior of the control loops is a model-based feed-forward torque control which is supported by a machine learning approach due to many advantages. The implementation in Matlab and the simulative evaluation are explained, which subsequently confirms the potential of this concept.

Sign in / Sign up

Export Citation Format

Share Document