<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The current lack of music core literacy in vocal music teaching needs to be solved, and this paper aims to improve this problem. In the paper, a hybrid attention module is added to the multi-channel of MFCC to extract the acoustic elements of the musical instruments, and after characterizing the musical instruments as a multi-view sequence, visual features and temporal features are fused, and a graph convolution module is added to extract the visual elements of the musical instruments, and the two are fused. After extracting the elements of musical instruments, the development of vocal fusion teaching of the two was analyzed by combining the gray correlation analysis method, and experiments were designed on the basis of which to investigate the extraction effect of the elements of musical instruments as well as the development of vocal fusion pedagogy. The results show that the average accuracy of instrumental elements of the multimodal extraction model is 0.919, which is improved by 0.17 compared with the Baseline classification accuracy, and the extraction accuracy can reach more than 90% for flute, percussion instrument, plucked instrument, wind instrument, suona, xiao, sheng, wind instrument, pipa, and erhu. The gray correlation of the fourth grade ranged from 0.75 to 0.88, with a high improvement in the same grade, and the gray correlation of different grades all ranged from 0.3 to 1.0, and the higher the grade, the better the development.</p>
</abstract>

The current lack of music core literacy in vocal music teaching needs to be solved, and this paper aims to improve this problem. In the paper, a hybrid attention module is added to the multi-channel of MFCC to extract the acoustic elements of the musical instruments, and after characterizing the musical instruments as a multi-view sequence, visual features and temporal features are fused, and a graph convolution module is added to extract the visual elements of the musical instruments, and the two are fused. After extracting the elements of musical instruments, the development of vocal fusion teaching of the two was analyzed by combining the gray correlation analysis method, and experiments were designed on the basis of which to investigate the extraction effect of the elements of musical instruments as well as the development of vocal fusion pedagogy. The results show that the average accuracy of instrumental elements of the multimodal extraction model is 0.919, which is improved by 0.17 compared with the Baseline classification accuracy, and the extraction accuracy can reach more than 90% for flute, percussion instrument, plucked instrument, wind instrument, suona, xiao, sheng, wind instrument, pipa, and erhu. The gray correlation of the fourth grade ranged from 0.75 to 0.88, with a high improvement in the same grade, and the gray correlation of different grades all ranged from 0.3 to 1.0, and the higher the grade, the better the development.

Integration of Instrumental Elements and Vocal Teaching Based on Music Core Literacy

Department of Performing Arts and Culture

Collage of Music for Sichuan University of Science & Engineering

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The current lack of music core literacy in vocal music teaching needs to be solved, and this paper aims to improve this problem. In the paper, a hybrid...

Integration of Instrumental Elements and Vocal Teaching Based on Music Core Literacy

Publicado en línea: 23 dic 2023

Páginas: -

Recibido: 23 ene 2023

Aceptado: 03 jul 2023

DOI: https://doi.org/10.2478/amns.2023.2.01587

Palabras clave
MFCC, Mixed attention, Multi-view sequences, Graph convolution module, Gray correlation analysis, Vocal music teaching

© 2023 Hua Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Integration of Instrumental Elements and Vocal Teaching Based on Music Core Literacy

Publicado en línea: 23 dic 2023

Páginas: -

Recibido: 23 ene 2023

Aceptado: 03 jul 2023

DOI: https://doi.org/10.2478/amns.2023.2.01587

Palabras claveMFCC, Mixed attention, Multi-view sequences, Graph convolution module, Gray correlation analysis, Vocal music teaching

© 2023 Hua Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Palabras clave
MFCC, Mixed attention, Multi-view sequences, Graph convolution module, Gray correlation analysis, Vocal music teaching