Learning Multi-instrument Classification with Partial Labels release_b6thuwjt5vbvfmc5hb5wcmftwa

by Amir Kenarsari Anhari

Released as a article .

2020  

Abstract

Multi-instrument recognition is the task of predicting the presence or absence of different instruments within an audio clip. A considerable challenge in applying deep learning to multi-instrument recognition is the scarcity of labeled data. OpenMIC is a recent dataset containing 20K polyphonic audio clips. The dataset is weakly labeled, in that only the presence or absence of instruments is known for each clip, while the onset and offset times are unknown. The dataset is also partially labeled, in that only a subset of instruments are labeled for each clip. In this work, we investigate the use of attention-based recurrent neural networks to address the weakly-labeled problem. We also use different data augmentation methods to mitigate the partially-labeled problem. Our experiments show that our approach achieves state-of-the-art results on the OpenMIC multi-instrument recognition task.
In text/plain format

Archived Files and Locations

application/pdf  148.1 kB
file_covzym3p6veojg7n2wccr2aedm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-01-24
Version   v1
Language   en ?
arXiv  2001.08864v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2fc458b0-c097-4ab3-89cd-271b34f37270
API URL: JSON