Research on Multimodal Music Emotion Recognition Method Based on Image Sequence

Zhao, Yu

doi:10.1155/2021/7087588

Cited by 7 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The specific process of the algorithm is determined based on the propagation of the forward neural network [30][31]. In the model training, the sample set   , 1, 2, ,…”

Section: Emotion Recognition Processmentioning

confidence: 99%

Research on the Comparative Development of Modern Popular Music and Traditional Music Culture in Colleges and Universities in the Age of Artificial Intelligence

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, the forward neural network multi-feature fusion algorithm is used to extract the emotional features of music culture on artificial intelligence technology, considering the diversity and intermittency of the emotional features of the study, which needs to be parameterized. In the forward neural network architecture, the activation value obtained by using the nonlinear activation function is used, and the results obtained are passed to the next layer of data to realize layer-by-layer forward computation, which leads to the back-propagation activation function. The music culture emotion classification model is constructed based on the propagation mode of the forward neural network to determine the emotion recognition process. The research object is selected, the research process is determined, and in order to ensure the true validity of the research, it is necessary to test the reliability and validity of the research design scheme and to develop an empirical analysis of the comparison between popular music and traditional music culture. The results show that on the model, especially in the recognition of sacred, sad, passionate emotion type of music classification accuracy reached more than 88.2%. This paper’s model can improve the classification accuracy of music emotion to a certain extent. In the ontological knowledge analysis of popular music and traditional music culture, all three editions of textbooks show that general knowledge of music is predominant and has a large proportion, appreciation knowledge and extended knowledge are also considerable, and music knowledge is the least and has a small proportion. This study demonstrates the synergistic development of traditional culture and modern popular music, which is of great significance to the development of music education in colleges and universities.

show abstract

“…The specific process of the algorithm is determined based on the propagation of the forward neural network [30][31]. In the model training, the sample set   , 1, 2, ,…”

Section: Emotion Recognition Processmentioning

confidence: 99%

Research on the Comparative Development of Modern Popular Music and Traditional Music Culture in Colleges and Universities in the Age of Artificial Intelligence

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…It can not only enhance the interactivity and teaching effectiveness of remote teaching platforms but also help break through the geographical and temporal constraints of traditional teaching models, providing learners with a personalized and convenient learning experience [7][8][9]. Furthermore, multimodal technology promotes the optimization of educational resources and the creation of highquality content, contributing to educational equity and quality improvement [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Remote Teaching Interaction Platforms Through Multimodal Image Recognition Technology

Fang,

Zhang

2024

View full text Add to dashboard Cite

In the context of the digital era, remote teaching has become an integral part of the global education system. Effective remote teaching relies on the high interactivity of interaction platforms and the precise delivery of teaching content, with multimodal image recognition technology playing a key role. This technology enhances the intelligence level of remote teaching platforms by integrating visual and textual information, providing a richer and more intuitive interactive experience for teachers and students. However, existing multimodal image recognition technologies still face challenges in accuracy, real-time performance, and semantic understanding, especially in complex teaching scenarios where the understanding and feedback on teaching content are not accurate enough, limiting the effectiveness of remote teaching interaction platforms. Addressing these limitations, this paper proposes a multimodal image alignment method based on a self-attention mechanism that effectively integrates visual information into an encoder-decoder model to achieve high consistency between images and teaching content. Additionally, a novel multimodal image annotation and recognition algorithm is introduced, considering both semantic information and visual saliency to achieve higher recognition accuracy and practicality. Experimental validation shows significant improvements in the accuracy and real-time performance of multimodal image recognition, providing strong technical support for remote teaching interaction platforms, optimizing the allocation of teaching resources, and enhancing the quality and efficiency of education.

show abstract

“…Students can practice on their own through wearable sensors that collect and recognize hand-playing data [6][7]. Teachers can analyze the training data to have a comprehensive grasp of the students' practice and provide feedback to the students [8]. The methods for piano gesture recognition mainly include visual recognition and data glove [9].…”

Section: Introductionmentioning

confidence: 99%

Piano Playing Gesture Recognition Based on Multiple Intelligences Theory

Zhang

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, firstly, in order to solve the piano playing recognition problem in the field of artificial intelligence, based on the theory of multiple intelligences, the VGG-16 deep network migration learning algorithm is applied to estimate and acquire the piano playing gesture posture. Secondly, combined with the Iterative Update Extended Kalman Filter (IUEKF) algorithm, the micro-inertial sensor fixation of the piano-playing gesture is realized, which in turn is conducive to improving the piano-playing gesture recognition accuracy. Then, we obtain real-time piano-playing gesture information through a Kinect somatosensory device, construct a piano-playing gesture recognition model based on migration learning on the basis of obtaining piano-playing gesture features, and confirm the effectiveness of the model through the experimental study of piano-playing recognition. The results show that in piano-playing gesture recognition, the recognition accuracy of this paper’s method remains above 0.9, and the application of this paper’s method can effectively improve the recognition accuracy of piano-playing gestures. On piano playing pedal action recognition, this paper’s method shows that the average F-measure scores of these two strategies are 0.924 and 0.944, respectively, which are better compared to other methods. This study provides an effective case for applying AI techniques to piano performance recognition and broadens the scope of AI applications.

show abstract

Research on Multimodal Music Emotion Recognition Method Based on Image Sequence

Cited by 7 publications

References 30 publications

Research on the Comparative Development of Modern Popular Music and Traditional Music Culture in Colleges and Universities in the Age of Artificial Intelligence

Research on the Comparative Development of Modern Popular Music and Traditional Music Culture in Colleges and Universities in the Age of Artificial Intelligence

Optimizing Remote Teaching Interaction Platforms Through Multimodal Image Recognition Technology

Piano Playing Gesture Recognition Based on Multiple Intelligences Theory

Contact Info

Product

Resources

About