Author
Qin Yao
Bio: Qin Yao is an academic researcher. The author has contributed to research in topics: Entropy (energy dispersal) & Entropy maximization. The author has co-authored 2 publications.
Papers
More filters
TL;DR: In this article, a negative entropy maximization (NEM) based method was proposed for well-posed speech and music separation, where the NEM was used instead of the Newton iteration method as the optimization algorithm to find the optimal matrix.
Abstract: With the rapid growth of digital music today, due to the complexity of the music itself, the ambiguity of the definition of music category, and the limited understanding of the characteristics of human auditory perception, the research on topics related to automatic segmentation of music is still in its infancy, while automatic music is still in its infancy. Segmentation is a prerequisite for fast and effective retrieval of music resources, and its potential application needs are huge. Therefore, topics related to automatic music segmentation have important research value. This paper studies an improved algorithm based on negative entropy maximization for well-posed speech and music separation. Aiming at the problem that the separation performance of the negative entropy maximization method depends on the selection of the initial matrix, the Newton downhill method is used instead of the Newton iteration method as the optimization algorithm to find the optimal matrix. By changing the descending factor, the objective function shows a downward trend, and the dependence of the algorithm on the initial value is reduced. The simulation experimental results show that the algorithm can separate the source signal well under different initial values. The average iteration time of the improved algorithm is reduced by 26.2%, the number of iterations is reduced by 69.4%, and the iteration time and the number of iterations are both small. Fluctuations within the range better solve the problem of sensitivity to the initial value. Experiments have proved that the new objective function can significantly improve the separation performance of neural networks. Compared with the existing music separation methods, the method in this paper shows excellent performance in both accompaniment and singing in separated music.
2 citations
TL;DR: In this paper, a music retrieval system based on the knowledge of music was proposed, and the feature extraction algorithm was analyzed. But the detailed design of the system was not discussed.
Abstract: This paper firstly introduces the basic knowledge of music, proposes the detailed design of a music retrieval system based on the knowledge of music, and analyzes the feature extraction algorithm a...
1 citations
Cited by
More filters
01 Jan 2022
TL;DR: The simulation results show that the audio classification performance of the hidden Markov model proposed in this paper has better performance, and the optimal classification accuracy is more than 90%.
Abstract: To facilitate professional users to find multimedia files composed of music information more quickly and realize audio frequency content information retrieval, this paper proposes a solution of automatic classification using HMM. Considering the traditional timbre features, the preprocessing process of speech signal is analyzed, and the common feature parameter extraction methods are compared to denoise audio information from the aspects of structure and state number. Then HMM model based on notes is used for training and recognition to realize the feature extraction of teaching audio/video files. The simulation results show that the audio classification performance of the hidden Markov model proposed in this paper has better performance, and the optimal classification accuracy is more than 90%.
2 citations
26 May 2023
TL;DR: In this paper , the authors proposed an automatic music tagging algorithm based on tag depth analysis, which uses the concept of tag depth to classify songs, and the length of these markers are then compared and assigned to different categories.
Abstract: With the rapid development of music social media, online music resources are rapidly increasing and music types are increasingly diversified. As an effective means to organize massive music data, rich music annotation information has become an important part of online music services. Automatic music tagging algorithm based on tag depth analysis is an automatic music tagging method that uses the concept of tag depth to classify songs. The algorithm starts with a set of songs, where each song is assigned one or more tags. The lengths of these markers are then compared and assigned to different categories. For example, if a song has three tags, it will be classified as pop / rock, dance and country music. If the song uses two tags, it will be classified as rock / pop and pop / rock, respectively. This process will continue until all songs have been classified by their tag depth and classified accordingly.
TL;DR: Wang et al. as discussed by the authors analyzed the promotion role of digital music and the development of mental health in colleges and universities, and proposed a new way of implementation for college mental health education.
Abstract: Abstract The interdisciplinary study of mental health education and digital music in colleges and universities is an indispensable part of China’s education discipline system. To solve the current problems of mental health education in colleges and universities, this paper analyzes the promotion role of digital music and the development of mental health in colleges and universities. The hierarchical analysis method is used to build a mental health assessment index system in colleges and universities. Using the VPMCD method, based on the intrinsic relationship between different index characteristics, a digital music-based psychological health assessment model for colleges and universities is established to assess the psychological health problems of college students. According to the psychological assessment results, the listening psychological intervention method is used to psychologically intervene with students. And by calculating the main melody of digital music materials, the type of music intervention materials used was determined. Experimental results: The listening psychological intervention method successfully led to the slow recovery of students with severe and moderate mental health problems and the complete recovery of students with mild psychological problems. 11 students (9.2% of the total) were completely cured of their psychological problems among the freshmen students in college A. The number of students who reduced their psychological problems was 86, accounting for 81.1% of the total. 26 students, accounting for 32.3% of the total, were completely cured of their psychological problems in their sophomore year at College A. The number of students who reduced their psychological problems was 56, accounting for 51.3% of the total. It proves that: digital music plays a supplementary role in college mental health education and proposes a new way of implementation for college mental health education. It promotes the diversified development of mental health education in colleges and universities as well as the cultivation of positive psychological qualities of college students and guides them to grow up positively and healthily.