Perceptual Evaluation of Neural Source-Filter Waveform Models versus Tacotron for 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: To what extent do neural source-filter waveform models outperform Tacotron-based systems in perceptual evaluation metrics for multi-instrument MIDI-to-audio generation?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.1/10.