An End-to-End Neural Network for Polyphonic Piano Music Transcription

By Siddharth Sigtia, Emmanouil Benetos, Simon E. Dixon. IEEE/ACM Transactions on Audio Speech and Language Processing, 2015

302 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Automatic Music Transcription: An Overview (2019, methodology): “[18] also used the aforementioned RNN– RBM as an MLM and combined the acoustic and language predictions using a probabilistic graphical model.”
Invariances and Data Augmentation for Supervised Music Transcription (2017, background): “The frequency-invariance ideas that lead to the best models presented in this paper are anticipated in [16, 13, 14].”
Onsets and Frames: Dual-Objective Piano Transcription (2017, methodology): “Previous framewise prediction models [13, 18] have treated frames as both independent and of equal importance, at least prior to being processed by a separate language model.”
Parallel Scheduled Sampling (2019, background): “tion 1 arXiv:1906.04331v2 [cs.CL] 21 Oct 2019 performance in other tasks such as video prediction (Finn et al., 2016), knowledge base completion (Miwa and Bansal, 2016) and piano music transcription (Sigtia et al., 2016). A key bottleneck in training models with Scheduled Sampling is its inherently ”
Convolutional recurrent neural networks for music classification (2016, background): “This structure was first proposed in [7] for document classification and later applied to image classification [8] and music transcription [9].”
Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection (2017, unknown): “This is consistent with the results presented in [31] on a similar task.”