Impact of Latent Dimensionality Scaling on Perceptual Quality in MIDI-to-Audio Synthesis

Speech synthesis and music audio generation from symbolic input differ in many aspects but share some similarities. In this study, we investigate how text-to-speech synthesis techniques can be used for piano MIDI-to-audio synthesis tasks. Our investigation includes Tacotron and neural source-filter waveform models as the basic components, with which we build MIDI-to-audio synthesis systems in similar ways to TTS frameworks. We also include reference systems using conventional sound modeling techniques such as sample-based and physical-modeling-based methods. The subjective experimental results

Research goal: What is the impact of scaling the latent dimensionality in Tacotron-like models on the perceptual quality (measured via MUSHRA scores) of MIDI-to-audio synthesis for polyphonic instruments?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.