Unconditional Audio Generation With Generative Adversarial Networks And Cycle Regularization
2020 · Jen-Yu Liu, Yu-Hua Chen, Yin-Cheng Yeh, et al.
Abstract
In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of noise vectors as input, it can generate mel-spectrograms of variable length. However, our previous listening test shows that the quality of the generated audio leaves room for improvement. The present paper extends and expands that previous work in the following aspects. First, we employ a hierarchical architecture in the generator to induce some structure in the temporal dimension. Second, we introduce a cycle regularization mechanism to the generator to avoid mode collapse. Third, we evaluate the performance of the new model not only for generating singing voices, but also for generating speech voices. Evaluation result shows that new model outperforms the prior one both objectively and subjectively. We also employ the model to unconditionally gene
Authors
(none)
Tags
Stats
Related papers
- Melgan: Generative Adversarial Networks For Conditional Waveform Synthesis (2019)0.00
- Improving Adversarial Waveform Generation Based Singing Voice Conversion With Harmonic Signals (2022)7.50
- Singgan: Generative Adversarial Network For High-fidelity Singing Voice Generation (2021)10.61
- SVSGAN: Singing Voice Separation Via Generative Adversarial Network (2017)0.00
- Samplernn: An Unconditional End-to-end Neural Audio Generation Model (2016)0.00
- Vocgan: A High-fidelity Real-time Vocoder With A Hierarchically-nested Adversarial Network (2020)12.54
- Hifi-wavegan: Generative Adversarial Network With Auxiliary Spectrogram-phase Loss For High-fidelity Singing Voice Generation (2022)0.00
- Multi-spectrogan: High-diversity And High-fidelity Spectrogram Generation With Adversarial Style Combination For Speech Synthesis (2020)0.00