Title: Opera audio understanding and synthesis via neural network models: from recognition to generation

Authors: Jie Pan

Addresses: Communication University of China, No. 3666, Hongjing Avenue, Jiangning District, Nanjing, Jiangsu, 211172, China; Nanjing University of Aeronautics and Astronautics, No. 29, Jiangjun Avenue, Jiangning District, Nanjing City, Jiangsu Province, 211106, China

Abstract: This study proposes a composite model for opera audio recognition and style generation. The model integrates chaotic fingerprint coding, deep neural networks, and generative networks for style transfer. The model uses a 20-bit chaotic audio fingerprint based on logistic mapping and time-frequency peaks. This technology can achieve efficient compression and robust recognition. The accuracy of method in a noisy environment is 92.3%, which is 12.5% higher than that of traditional methods. The DNN-LightGBM cascade structure effectively models features and efficiently classifies features in 19 opera categories with an accuracy of 88-95%. In terms of style transfer, generative adversarial network with orthogonal style loss function separates timbre and style and reduce Mel cepstral distortion by 18.3%, from 5.24 to 4.87. In addition, spectrum-based unsupervised linear style encoder improves the robustness of the transfer by 23.6% under various accompaniment conditions. The framework has high recognition accuracy, high-quality style transfer, and strong adaptability.

Keywords: opera audio; neural network models; audio recognition; audio synthesis; generative modelling.

DOI: 10.1504/IJART.2026.151922

International Journal of Arts and Technology, 2026 Vol.16 No.1, pp.1 - 28

Received: 20 Apr 2025
Accepted: 14 May 2025
Published online: 26 Feb 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article