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

<p>In recent years, artificial intelligence technology has been deeply integrated into college education to comply with the call for teaching reform. The research first uses endpoint detection and Mel frequency cepstrum coefficients to realize the recognition and extraction of vocal music feature signals. Then it uses a deep convolutional neural network to output the extracted signals to complete the recognition and error correction of different vocal music. Finally, different vocal audio is used as a sample to deeply analyze the recognition of various styles of vocal music, as well as the recognition and error correction of music. The model in this paper has a more satisfactory effect on vocal music recognition and music style classification. The recognition rate of vocal music under different signal-to-noise ratios is above 90%. It can also well realize the error correction of vocal music and accurately judge the time value (95%) and pitch (93.57%) of the playing, which reflects a high application value in vocal music teaching. The use of deep learning in vocal music recognition and error correction in college vocal music education can assist vocal music learners and decrease the work intensity of vocal music educators.</p>
</abstract>

In recent years, artificial intelligence technology has been deeply integrated into college education to comply with the call for teaching reform. The research first uses endpoint detection and Mel frequency cepstrum coefficients to realize the recognition and extraction of vocal music feature signals. Then it uses a deep convolutional neural network to output the extracted signals to complete the recognition and error correction of different vocal music. Finally, different vocal audio is used as a sample to deeply analyze the recognition of various styles of vocal music, as well as the recognition and error correction of music. The model in this paper has a more satisfactory effect on vocal music recognition and music style classification. The recognition rate of vocal music under different signal-to-noise ratios is above 90%. It can also well realize the error correction of vocal music and accurately judge the time value (95%) and pitch (93.57%) of the playing, which reflects a high application value in vocal music teaching. The use of deep learning in vocal music recognition and error correction in college vocal music education can assist vocal music learners and decrease the work intensity of vocal music educators.

Constructing a Theoretical Methodological System for Vocal Music Education in Colleges and Universities in the Context of Deep Learning Algorithms

Applied Mathematics and Nonlinear Sciences

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

In recent years, artificial intelligence technology has been deeply integrated into college education to comply with the call for teaching reform. The research...

Constructing a Theoretical Methodological System for Vocal Music Education in Colleges and Universities in the Context of Deep Learning Algorithms

Online veröffentlicht: 15. Mai 2024

Seitenbereich: -

Eingereicht: 17. Jan. 2024

Akzeptiert: 01. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-1091

Schlüsselwörter
Mel-frequency cepstrum coefficients, Convolutional neural network, Deep learning, Vocal music recognition and error correction, Vocal music education

© 2024 Weifang Zhang, published by Sciendo

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

Constructing a Theoretical Methodological System for Vocal Music Education in Colleges and Universities in the Context of Deep Learning Algorithms

Online veröffentlicht: 15. Mai 2024

Seitenbereich: -

Eingereicht: 17. Jan. 2024

Akzeptiert: 01. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-1091

SchlüsselwörterMel-frequency cepstrum coefficients, Convolutional neural network, Deep learning, Vocal music recognition and error correction, Vocal music education

© 2024 Weifang Zhang, published by Sciendo

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

Schlüsselwörter
Mel-frequency cepstrum coefficients, Convolutional neural network, Deep learning, Vocal music recognition and error correction, Vocal music education