music-1

Drum Transcription

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in drum-transcription-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find drum-transcription-1 models and implementations

Datasets

E-GMD

ENST Drums

YourMT3 Dataset

Subtasks

No subtasks available.

Most implemented papers

Towards multi-instrument drum transcription

Richard Vogl, G. Widmer, Peter Knees•Sun Jun 17 2018

Convolutional and convolutional recurrent neural networks are trained to transcribe a wider range of drum instruments using a large-scale synthetic dataset for drum transcription.

21

Content

0

Paper Graph

Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset

Jesse Engel, Curtis Hawthorne, Lee F. Callender•Tue Mar 31 2020

This work optimize classifiers for downstream generation by predicting expressive dynamics (velocity) and shows with listening tests that they produce outputs with improved perceptual quality, despite achieving similar results on classification metrics.

26 0

Paper Graph

Ultra-light deep MIR by trimming lottery tickets

Adrien Bitton, P. Esling, Th'eis Bazin, Tristan Carsault, Ninon Devis•Thu Jul 30 2020

This paper proposes a model pruning method based on the lottery ticket hypothesis, modify the original approach to allow for explicitly removing parameters, through structured trimming of entire units, which leads to models which are effectively lighter in terms of size, memory and number of operations.

2 0

Paper Graph

YourMT3+: Multi-Instrument Music Transcription with Enhanced Transformer Architectures and Cross-Dataset STEM Augmentation

Emmanouil Benetos, Sungkyun Chang, Holger Kirchhoff, Simon Dixon•Thu Jul 04 2024

Y ourMT3+, a suite of models for enhanced multi-instrument music transcription based on the recent language token decoding approach of MT3, is introduced, enhancing its encoder by adopting a hierarchical attention transformer in the time-frequency domain and integrating a mixture of experts.

9 0

Paper Graph

Adding a benchmark result helps the community track progress.