EXPLOITING PRE-TRAINED FEATURE NETWORKS FOR GENERATIVE ADVERSARIAL NETWORKS IN AUDIO-DOMAIN LOOP GENERATION.
Gespeichert in:
| Titel: | EXPLOITING PRE-TRAINED FEATURE NETWORKS FOR GENERATIVE ADVERSARIAL NETWORKS IN AUDIO-DOMAIN LOOP GENERATION. |
|---|---|
| Autoren: | Yen-Tung Yeh, Bo-Yu Chen, Yi-Hsuan Yang |
| Quelle: | International Society for Music Information Retrieval Conference Proceedings; 2022, p132-140, 9p |
| Schlagwörter: | GENERATIVE adversarial networks, MUSICAL composition, MUSICAL analysis, MUSIC data processing, AUDIO acoustics |
| Abstract: | While generative adversarial networks (GANs) have been widely used in research on audio generation, the training of a GAN model is known to be unstable, time consuming, and data inefficient. Among the attempts to ameliorate the training process of GANs, the idea of Projected GAN emerges as an effective solution for GAN-based image generation, establishing the state-of-the-art in different image applications. The core idea is to use a pre-trained classifier to constrain the feature space of the discriminator to stabilize and improve GAN training. This paper investigates whether Projected GAN can similarly improve audio generation, by evaluating the performance of a StyleGAN2-based audio-domain loop generation model with and without using a pre-trained feature space in the discriminator. Moreover, we compare the performance of using a general versus domain-specific classifier as the pretrained audio classifier. With experiments on unconditional one-bar drum loop and synth loop generation, we show that a general audio classifier works better, and that with Projected GAN our loop generation models can converge around 5 times faster without performance degradation. [ABSTRACT FROM AUTHOR] |
| Copyright of International Society for Music Information Retrieval Conference Proceedings is the property of Ubiquity Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Datenbank: | Complementary Index |
Schreiben Sie den ersten Kommentar!