Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
This work addresses the challenge of generating and transcribing polyphonic music for applications in music technology, though it appears incremental as it builds on existing neural network methods.
The authors tackled the problem of modeling high-dimensional symbolic sequences for polyphonic music by introducing a probabilistic model based on a recurrent neural network, which outperformed traditional models on realistic datasets and improved transcription accuracy.
We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our approach outperforms many traditional models of polyphonic music on a variety of realistic datasets. We show how our musical language model can serve as a symbolic prior to improve the accuracy of polyphonic transcription.