Samplernn: An Unconditional End-to-end Neural Audio Generation Model

Abstract

In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very long time spans, on three datasets of different nature. Human evaluation on the generated samples indicate that our model is preferred over competing models. We also show how each component of the model contributes to the exhibited performance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymehri2016samplernn

Related papers

• Unconditional Audio Generation With Generative Adversarial Networks And Cycle Regularization (2020)9.41
• Wavenet: A Generative Model For Raw Audio (2016)0.00
• Melnet: A Generative Model For Audio In The Frequency Domain (2019)0.00
• Uniaudio: An Audio Foundation Model Toward Universal Audio Generation (2023)5.56
• Audioldm 2: Learning Holistic Audio Generation With Self-supervised Pretraining (2023)0.00
• An Unsupervised Autoregressive Model For Speech Representation Learning (2019)17.26
• Gansynth: Adversarial Neural Audio Synthesis (2019)0.00
• Audiolm: A Language Modeling Approach To Audio Generation (2022)18.91