599 citations · 1.2k across the 9 of their papers we have counts for
9 papers
VampNet: Music Generation via Masked Acoustic Token Modeling
Hugo Flores Garcia, Prem Seetharaman, Rithesh Kumar +1
We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which…
High-Fidelity Audio Compression with Improved RVQGAN
Rithesh Kumar, Prem Seetharaman, Alejandro Luebs +2
Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model…
Chunked Autoregressive GAN for Conditional Waveform Synthesis
Max Morrison, Rithesh Kumar, Kundan Kumar +3
Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative model…
NU-GAN: High resolution neural upsampling with GAN
Rithesh Kumar, Kundan Kumar, Vicki Anand +2
In this paper, we propose NU-GAN, a new method for resampling audio from lower to higher sampling rates (upsampling). Audio upsampling is an important problem since productionizing…
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Kundan Kumar, Rithesh Kumar, Thibault de Boissiere +6
Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is poss…
Maximum Entropy Generators for Energy-Based Models
Rithesh Kumar, Sherjil Ozair, Anirudh Goyal +2
Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In this work, we propose learning both the e…