Residual Shuffle-Exchange Network is an efficient alternative to models using an attention mechanism that allows the modelling of long-range dependencies in sequences in O(n log n) time. This model achieved state-of-the-art performance on the MusicNet dataset for music transcription while being able to run inference on a single GPU fast enough to be suitable for real-time audio processing.
Source: Residual Shuffle-Exchange Networks for Fast Processing of Long SequencesPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Matrix Completion | 1 | 20.00% |
Retrieval | 1 | 20.00% |
LAMBADA | 1 | 20.00% |
Language Modelling | 1 | 20.00% |
Music Transcription | 1 | 20.00% |