Learning Temporal Dependencies in Data Using a DBN-BLSTM
This addresses the issue of inadequate temporal modeling in deep learning for auditory data, though it appears incremental as it combines existing methods.
The paper tackles the problem of modeling temporal dependencies in data by proposing a DBN-BLSTM architecture, achieving state-of-the-art results in music generation.
Since the advent of deep learning, it has been used to solve various problems using many different architectures. The application of such deep architectures to auditory data is also not uncommon. However, these architectures do not always adequately consider the temporal dependencies in data. We thus propose a new generic architecture called the Deep Belief Network - Bidirectional Long Short-Term Memory (DBN-BLSTM) network that models sequences by keeping track of the temporal information while enabling deep representations in the data. We demonstrate this new architecture by applying it to the task of music generation and obtain state-of-the-art results.