Generative timbre spaces with variational audio synthesis
share
Timbre spaces have been used in music perception to study the relationships between instruments based on dissimilarity ratings. However, these spaces do not generalize, need to be reconstructed for each novel example and are not continuous, preventing audio synthesis. In parallel, generative models have aimed to provide methods for synthesizing novel timbres. However, these systems do not provide an explicit control structure, nor do they provide an understanding of their inner workings and are not related to any perceptually relevant information. Here, we show that Variational Auto-Encoders (VAE) can alleviate these limitations by constructing generative timbre spaces. To do so, we adapt VAEs to create a generative latent space, while using perceptual ratings from timbre studies to regularize the organization of this space. The resulting space allows to analyze novel instruments, while being able to synthesize audio from any point of this space. We introduce a specific regularization allowing to directly enforce given similarity ratings onto these spaces. We compare the resulting space to existing timbre spaces and show that they provide almost similar distance relationships. We evaluate several spectral transforms and show that the Non-Stationary Gabor Transform (NSGT) provides the highest correlation to timbre spaces and the best quality of synthesis. We show that these spaces can generalize to novel instruments and can generate any path between instruments to understand their timbre relationships. As these spaces are continuous, we study how the traditional acoustic descriptors behave along the latent dimensions. We show that descriptors have an overall non-linear topology, but follow a locally smooth evolution. Based on this, we introduce a method for descriptor-based synthesis and show that we can control the descriptors of an instrument while keeping its timbre structure.
READ FULL TEXT