English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a deep convolutional GAN which leverages techniques fromMP3/Vorbis audio compression to produce long, high-quality audio samples withlong-range coherence. The model uses a Modified Discrete Cosine Transform(MDCT) data representation, which includes all phase information. Phasegeneration is hence integral part of the model. We leverage the auditorymasking and psychoacoustic perception limit of the human ear to widen the truedistribution and stabilize the training process. The model architecture is adeep 2D convolutional network, where each subsequent generator model blockincreases the resolution along the time axis and adds a higher octave along thefrequency axis. The deeper layers are connected with all parts of the outputand have the context of the full track. This enables generation of sampleswhich exhibit long-range coherence. We use MP3net to create 95s stereo trackswith a 22kHz sample rate after training for 250h on a single Cloud TPUv2. Anadditional benefit of the CNN-based model architecture is that generation ofnew songs is almost instantaneous.

MP3net: coherent, minute-long music generation from raw audio with a simple convolutional GAN