Two Web Toolkits for Multimodal Piano Performance Dataset Acquisition and Fingering Annotation
By: Junhyung Park , Yonghyun Kim , Joonhyung Bae and more
Potential Business Impact:
Records piano playing with sound, video, and finger movements.
Piano performance is a multimodal activity that intrinsically combines physical actions with the acoustic rendition. Despite growing research interest in analyzing the multimodal nature of piano performance, the laborious process of acquiring large-scale multimodal data remains a significant bottleneck, hindering further progress in this field. To overcome this barrier, we present an integrated web toolkit comprising two graphical user interfaces (GUIs): (i) PiaRec, which supports the synchronized acquisition of audio, video, MIDI, and performance metadata. (ii) ASDF, which enables the efficient annotation of performer fingering from the visual data. Collectively, this system can streamline the acquisition of multimodal piano performance datasets.
Similar Papers
PianoVAM: A Multimodal Piano Performance Dataset
Sound
Helps computers learn to play piano by watching.
Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcription
Sound
Makes computers learn guitar music from fake sounds.
PianoBind: A Multimodal Joint Embedding Model for Pop-piano Music
Sound
Helps computers understand piano music's feelings.