Learning To Generate Piano Music With Sustain Pedals
This work addresses a gap in symbolic music generation for piano by incorporating sustain pedal information, but it is incremental as it builds on existing models and uses inferred data.
The authors tackled the problem of generating symbolic piano music with sustain pedal information, which is rarely considered in existing generative models, by using a transcription model to extract pedal data and modifying a Transformer decoder to incorporate it. The results indicate potential for improvement and highlight the importance of including sustain pedals in piano performance generation tasks.
Recent years have witnessed a growing interest in research related to the detection of piano pedals from audio signals in the music information retrieval community. However, to our best knowledge, recent generative models for symbolic music have rarely taken piano pedals into account. In this work, we employ the transcription model proposed by Kong et al. to get pedal information from the audio recordings of piano performance in the AILabs1k7 dataset, and then modify the Compound Word Transformer proposed by Hsiao et al. to build a Transformer decoder that generates pedal-related tokens along with other musical tokens. While the work is done by using inferred sustain pedal information as training data, the result shows hope for further improvement and the importance of the involvement of sustain pedal in tasks of piano performance generations.