High-dimensional sequence transduction

We investigate the problem of transforming an input sequence into a high-dimensional output sequence in order to transcribe polyphonic audio music into symbolic notation. We introduce a probabilistic model based on a recurrent neural network that is able to learn real-istic output distributions given the input and we devise an efficient algorithm to search for the global mode of that distribution. The re-sulting method produces musically plausible transcriptions even un-der high levels of noise and drastically outperforms previous state-of-the-art approaches on five datasets of synthesized sounds and real recordings, approximately halving the test error rate. Index Terms — Sequence transduction, restricted Boltzmann machine, recurrent neural network, polyphonic transcription 1