# Conditioning Autoencoder Latent Spaces for Real-Time Timbre Interpolation and Synthesis

arXiv: https://arxiv.org/abs/2001.11296 · HTML: https://mlsanity.com/paper/2001.11296/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2020.

## Built on by (most cited first, 4 of 4)

- [Timbre transfer using image-to-image denoising diffusion implicit models](https://mlsanity.com/paper/2307.04586/) (2023)
- [CAESynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders](https://mlsanity.com/paper/2111.05174/) (2021)
- [Sound Design Strategies for Latent Audio Space Explorations Using Deep Learning Architectures](https://mlsanity.com/paper/2305.15571/) (2023)
- [An investigation of the reconstruction capacity of stacked convolutional autoencoders for log-mel-spectrograms](https://mlsanity.com/paper/2301.07665/) (2023)

## Abstract (arXiv)

We compare standard autoencoder topologies' performances for timbre generation. We demonstrate how different activation functions used in the autoencoder's bottleneck distributes a training corpus's embedding. We show that the choice of sigmoid activation in the bottleneck produces a more bounded and uniformly distributed embedding than a leaky rectified linear unit activation. We propose a one-hot encoded chroma feature vector for use in both input augmentation and latent space conditioning. We measure the performance of these networks, and characterize the latent embeddings that arise from the use of this chroma conditioning vector. An open source, real-time timbre synthesis algorithm in Python is outlined and shared.