Catch-A-Waveform: Learning to Generate Audio from a Single Short Example

by   Gal Greshler, et al.

Models for audio generation are typically trained on hours of recordings. Here, we illustrate that capturing the essence of an audio source is typically possible from as little as a few tens of seconds from a single training signal. Specifically, we present a GAN-based generative model that can be trained on one short audio signal from any domain (e.g. speech, music, etc.) and does not require pre-training or any other form of external supervision. Once trained, our model can generate random samples of arbitrary duration that maintain semantic similarity to the training waveform, yet exhibit new compositions of its audio primitives. This enables a long line of interesting applications, including generating new jazz improvisations or new a-cappella rap variants based on a single short example, producing coherent modifications to famous songs (e.g. adding a new verse to a Beatles song based solely on the original recording), filling-in of missing parts (inpainting), extending the bandwidth of a speech signal (super-resolution), and enhancing old recordings without access to any clean training example. We show that in all cases, no more than 20 seconds of training audio commonly suffice for our model to achieve state-of-the-art results. This is despite its complete lack of prior knowledge about the nature of audio signals in general.



There are no comments yet.


page 2

page 3

page 4

page 7

page 8

page 9

page 15

page 16


Audio Super Resolution using Neural Networks

We introduce a new audio processing technique that increases the samplin...

WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolution

Audio super-resolution is the task of constructing a high-resolution (HR...

Transferring neural speech waveform synthesizers to musical instrument sounds generation

Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the n...

Quasi-Periodic WaveNet: An Autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Network

In this paper, a pitch-adaptive waveform generative model named Quasi-Pe...

Learning music audio representations via weak language supervision

Audio representations for music information retrieval are typically lear...

Speech bandwidth extension with WaveNet

Large-scale mobile communication systems tend to contain legacy transmis...

GIPFA: Generating IPA Pronunciation from Audio

Transcribing spoken audio samples into International Phonetic Alphabet (...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.