Semi-recurrent Cnn-based VAE-GAN For Sequential Data Generation

Abstract

A semi-recurrent hybrid VAE-GAN model for generating sequential data is introduced. In order to consider the spatial correlation of the data in each frame of the generated sequence, CNNs are utilized in the encoder, generator, and discriminator. The subsequent frames are sampled from the latent distributions obtained by encoding the previous frames. As a result, the dependencies between the frames are maintained. Two testing frameworks for synthesizing a sequence with any number of frames are also proposed. The promising experimental results on piano music generation indicates the potential of the proposed framework in modeling other sequential data such as video.

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keyakbari2018semi

Related papers

• Disentangled Sequential Autoencoder (2018)0.00
• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• VQCPC-GAN: Variable-length Adversarial Audio Synthesis Using Vector-quantized Contrastive Predictive Coding (2021)5.84
• Midi-sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN Networks For Symbolic Single-track Music Generation (2019)0.00
• Audio Input Generates Continuous Frames To Synthesize Facial Video Using Generative Adiversarial Networks (2022)0.00
• Stochastic Wavenet: A Generative Latent Variable Model For Sequential Data (2018)0.00
• Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
• Conditional Hybrid GAN For Sequence Generation (2020)0.00