SVSGAN: Singing Voice Separation Via Generative Adversarial Network

Abstract

Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice separation using the generative adversarial network (GAN) with a time-frequency masking function. The mixture spectra is considered to be a distribution and is mapped to the clean spectra which is also considered a distribtution. The approximation of distributions between mixture spectra and clean spectra is performed during the adversarial training process. In contrast with current deep learning approaches for source separation, the parameters of the proposed framework are first initialized in a supervised setting and then optimized by the training procedure of GAN in an unsupervised setting. Experimental results on three datasets (MIR-1K, iKala and DSD100) show that performance can be improved by the proposed framework consisting of conventional netwo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfan2017svsgan

Related papers

• Single-channel Signal Separation And Deconvolution With Generative Adversarial Networks (2019)6.77
• Singgan: Generative Adversarial Network For High-fidelity Singing Voice Generation (2021)10.61
• Hifi-wavegan: Generative Adversarial Network With Auxiliary Spectrogram-phase Loss For High-fidelity Singing Voice Generation (2022)0.00
• Generative Adversarial Source Separation (2017)11.76
• Mandarin Singing Voice Synthesis With Denoising Diffusion Probabilistic Wasserstein GAN (2022)6.34
• Wgansing: A Multi-voice Singing Voice Synthesizer Based On The Wasserstein-gan (2019)11.08
• Deep Variational Generative Models For Audio-visual Speech Separation (2020)0.00
• GSEP: A Robust Vocal And Accompaniment Separation System Using Gated CBHG Module And Loudness Normalization (2020)0.00