Uneingeschränkter Zugang

Research on Deep Learning Model Training and Cross-Ethnic Cultural Interaction Mechanism of Daur Music Inheritance in Heilongjiang Province

Baixue Zhang

Baixue Zhang

School of Music and Dance, Qiqihar UniversityQiqihar, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Zhang, Baixue
  
23. Sept. 2025
Research on Deep Learning Model Training and Cross-Ethnic Cultural Interaction Mechanism of Daur Music Inheritance in Heilongjiang Province's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
COVER HERUNTERLADEN
Online veröffentlicht: 23. Sept. 2025
Eingereicht: 09. Jan. 2025
Akzeptiert: 04. Mai 2025
DOI: https://doi.org/10.2478/amns-2025-0993
Schlüsselwörter
© 2025 Baixue Zhang, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

The Daur music culture
The Daur music culture

Figure 2.

The economic and ethnic cultural relations of ethnic minorities
The economic and ethnic cultural relations of ethnic minorities

Figure 3.

Generate the antagonistic network model
Generate the antagonistic network model

Figure 4.

Music generation model
Music generation model

Figure 5.

Comparison of loss values of model training
Comparison of loss values of model training

Figure 6.

The weight distribution of the discriminator under different strategies
The weight distribution of the discriminator under different strategies

Figure 7.

Subjective score evaluation visual results
Subjective score evaluation visual results

Model comparison

Model Parameter quantity (Million) Convergence number (epoch) Training time (s) Unit time (s)
SR-CNN-VAEGAN 12.11 350 64542 215.2
Music VAE 4.62 653 25154 42.3
MIDI-GAN(Ours) 2.13 300 6054 21.5

The music generated by different models is compared to the objective index

Model PPL UPG GC EBR
mLSTM 2.26 9.35 0.65 0.25
Transformer 1.79 9.27 0.87 0.19
SR-CNN-VAEGAN 1.76 9.34 0.84 0.18
Music VAE 1.72 8.75 0.83 0.15
MIDI-GAN(Ours) 1.70 8.43 0.81 0.11
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
1 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Biologie, Biologie, andere, Mathematik, Angewandte Mathematik, Mathematik, Allgemeines, Physik, Physik, andere
Zeitschrift RSS Feed