Brief

A C++ implementation of Meta's EnCodec audio codec has been developed, aiming for portability and high performance without external machine learning runtimes. This project, available on GitHub, compiles model weights directly into the binary for easier integration into CMake projects. The developer is seeking feedback on the implementation, which reportedly matches or exceeds the performance of ONNX Runtime. AI

Researchers have developed a new system that converts expressive drum grids, a detailed MIDI format, into realistic drum audio. This method utilizes a Transformer model to predict discrete codes from a neural audio codec, which are then decoded into sound. Experiments with codecs like EnCodec, DAC, and X-Codec show that the choice of audio representation significantly impacts the quality of the synthesized drums. The system was trained and evaluated on the E-GMD dataset, demonstrating codec-token prediction as a viable approach for percussive synthesis. AI