The NES Music Database: A multi-instrumental dataset with expressive performance attributes
This addresses the problem of lacking expressive performance data in music generation research for AI and music communities, though it is incremental as it builds on existing datasets by adding specific attributes.
The paper introduces the Nintendo Entertainment System Music Database (NES-MDB), a large dataset with musical scores and expressive performance attributes for multi-instrumental songs, enabling separate study of composition and performance tasks in music generation, and provides a tool for rendering NES-style audio along with baselines for these tasks.
Existing research on music generation focuses on composition, but often ignores the expressive performance characteristics required for plausible renditions of resultant pieces. In this paper, we introduce the Nintendo Entertainment System Music Database (NES-MDB), a large corpus allowing for separate examination of the tasks of composition and performance. NES-MDB contains thousands of multi-instrumental songs composed for playback by the compositionally-constrained NES audio synthesizer. For each song, the dataset contains a musical score for four instrument voices as well as expressive attributes for the dynamics and timbre of each voice. Unlike datasets comprised of General MIDI files, NES-MDB includes all of the information needed to render exact acoustic performances of the original compositions. Alongside the dataset, we provide a tool that renders generated compositions as NES-style audio by emulating the device's audio processor. Additionally, we establish baselines for the tasks of composition, which consists of learning the semantics of composing for the NES synthesizer, and performance, which involves finding a mapping between a composition and realistic expressive attributes.