Speech-Music Classification Model Based on Improved Neural Network and Beat Spectrum

doi:10.14569/IJACSA.2023.0140706

CQUET-IR

	Speech-Music Classification Model Based on Improved Neural Network and Beat Spectrum
	Huang, Chun 1; Wei, HeFu 2
	2023-07
发表期刊	International Journal of Advanced Computer Science and Applications
ISSN	2158-107X
EISSN	2156-5570
卷号	14 期号:7 页码:52-64
摘要	A speech-music classification method according to a developed neural system and beat spectrum is proposed to achieve accurate classification of speech-music through preemphasis, endpoint detection, framing, windowing and other steps to preprocess and collect vocal music signals. After fast Fourier transforms and triangle filter processing, the Mel frequency cepstrum coefficient (MFCC) is obtained, and a discrete cosine transform is performed to obtain the signal MFCC characteristic parameters. After calculating the similarity of feature parameters through cosine similarity, the signal similarity matrix is obtained, based on which the vocal music beat spectrum is obtained. The residual structure is optimized by adding Swish and max-out activation functions, respectively, between convolutional neural network layers to build residual convolution layers and deepen the number of convolution layers. The connected time series classification (CTC) is used as the objective loss function. It is applied to the softmax layer to build a deep optimization residual convolutional neural network for speech-music classification model. The pitch spectrum of vocal music is used as the input information of the model to realize the vocal music classification. The experiment proves that the classification accuracy of the design model is higher than 99%; when the iteration reaches 1200, the training loss approaches 0; when the signal-to-noise ratio is 180dB, the sensitivity and specificity are 99.98% and 99.96%, respectively; the accuracy of voice music classification is higher than 99%, and the running time is 0.48 seconds. It has been proven that the model has high classification accuracy, low training loss, good sensitivity and special effects, and can effectively achieve the classification of speech-music.
关键词	Vocal music classification model beat spectrum feature parameter extraction cosine similarity convolutional neural network
DOI	10.14569/IJACSA.2023.0140706
收录类别	ESCI ; EI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Theory & Methods
WOS记录号	WOS:001047155700001
出版者	SCIENCE & INFORMATION SAI ORGANIZATION LTD
EI入藏号	20233514647000
EI主题词	Convolution
EI分类号	716.1 Information Theory and Signal Processing ; 723 Computer Software, Data Handling and Applications ; 723.5 Computer Applications ; 751.5 Speech ; 903.1 Information Sources and Analysis ; 921.3 Mathematical Transformations ; 921.6 Numerical Methods ; 971 Social Sciences
原始文献类型	Article
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.cqcet.edu.cn/handle/39TD4454/18000
专题	重庆电子科技职业大学
作者单位	1.Gen Educ & Int Coll, Chongqing Coll Elect Engn, Chongqing 400031, Peoples R China; 2.Arts Coll Sichuan Univ, Chengdu 401331, Peoples R China
推荐引用方式 GB/T 7714	Huang, Chun,Wei, HeFu. Speech-Music Classification Model Based on Improved Neural Network and Beat Spectrum[J]. International Journal of Advanced Computer Science and Applications,2023,14(7):52-64.
APA	Huang, Chun,&Wei, HeFu.(2023).Speech-Music Classification Model Based on Improved Neural Network and Beat Spectrum.International Journal of Advanced Computer Science and Applications,14(7),52-64.
MLA	Huang, Chun,et al."Speech-Music Classification Model Based on Improved Neural Network and Beat Spectrum".International Journal of Advanced Computer Science and Applications 14.7(2023):52-64.