Piano Accompaniment Generation
This project explores what mixed AI models can learn from real piano accompaniment performances, including musical patterns, coherence based on song structure, and expressive articulation by the pianist. We are investigating what can be achieved using AI models and a very limited dataset.
Demos are available for audition below.
Copyright notice: I do not claim ownership of the underlying song compositions or recordings used in these demos, and I reserve copyright in the original, project-generated MIDI accompaniment outputs to the extent permitted by law. The materials are presented solely for academic and research purposes consistent with fair use; full-length excerpts are provided because the research evaluates accompaniment coherence and section-level structure across entire songs.
Demos
The following demos use the Chinese pop song Ren Jian Yan Huo (Chinese: 人间烟火) by singer Cheng Xiang (程响) for academic evaluation only. Vocals are included solely to show alignment with the piano accompaniment; the vocal track is intentionally reduced by 15 dB to highlight the piano, and no other post-processing is applied. The training dataset focuses on Chinese pop, so Ren Jian Yan Huo was selected to match that data bias, and it is one of my favorite songs.
Selected demo tracks (MP3) with corresponding MIDI files. I am not a musician, so the comments below are technical rather than artistic, focusing on factors such as alignment with training data statistics, per-song pattern repetition, and whether patterns match their intended roles.
All MIDI files in these demos are time-aligned to the vocal track and preserve the full articulation from the original live pianist performance. Because the performances are unquantized, note onsets will not fall exactly on a rigid time grid—this is expected and reflects natural human timing and expression.
Sample of Earlier Style Support
This is a sample from an earlier version. Each style uses more pattern options, which can sound more creative, but it often lacks consistency across sections and phrases.
| MIDI
12 Styles Currently Supported
Currently we support the following style keywords, selected to reduce overlap and to have sufficient samples in the dataset for evaluation.
Publications
To be updated.