Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration
Researchers have developed a novel system for generative sound synthesis that combines Quality Diversity (QD) algorithms with a supervised discriminative model. This approach, inspired by the Innovation Engine algorithm, automates the search for diverse and innovative sounds by leveraging evolutionary processes. The study introduces a new method using multiple specialized Compositional Pattern Producing Networks (CPPNs) with Digital Signal Processing (DSP) graphs, achieving comparable performance to single-CPPN setups while simplifying the networks. AI
IMPACT Introduces novel evolutionary algorithms for creative audio generation, potentially aiding composers and sound designers.