Melgan-vc: Voice Conversion And Audio Style Transfer On Arbitrarily Long Samples Using Spectrograms
2019 · Marco Pasini
Abstract
Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method that relies on non-parallel speech data and is able to convert audio signals of arbitrary length from a source voice to a target voice. We firstly compute spectrograms from waveform data and then perform a domain translation using a Generative Adversarial Network (GAN) architecture. An additional siamese network helps preserving speech information in the translation process, without sacrificing the ability to flexibly model the style of the target speaker. We test our framework with a dataset of clean speech recordings, as well as with a collection of noisy real-world speech examples. Finally, we apply the same method to perform music style transfer, translating arbitrarily long music samples from one genre to another, and showing that our framework is
Authors
(none)
Tags
Stats
Related papers
- Subband-based Generative Adversarial Network For Non-parallel Many-to-many Voice Conversion (2022)0.00
- Stylemelgan: An Efficient High-fidelity Adversarial Vocoder With Temporal Adaptive Normalization (2020)13.05
- Starganv2-vc: A Diverse, Unsupervised, Non-parallel Framework For Natural-sounding Voice Conversion (2021)13.70
- Universal Melgan: A Robust Neural Vocoder For High-fidelity Waveform Generation In Multiple Domains (2020)0.00
- Cyclegan-vc3: Examining And Improving Cyclegan-vcs For Mel-spectrogram Conversion (2020)14.02
- Vocgan: A High-fidelity Real-time Vocoder With A Hierarchically-nested Adversarial Network (2020)12.54
- Stargan-vc: Non-parallel Many-to-many Voice Conversion With Star Generative Adversarial Networks (2018)18.09
- Maskcyclegan-vc: Learning Non-parallel Voice Conversion With Filling In Frames (2021)0.00