Optical Music Recognition by Recurrent Neural Networks

被引：3
|
作者：
Baro, Arnau [1 ]
Riba, Pau [1 ]
Calvo-Zaragoza, Jorge [2 ]
Fornes, Alicia [1 ]
机构：
[1] Univ Autonoma Barcelona, Comp Vis Ctr, Comp Sci Dept, Bellaterra, Catalonia, Spain
[2] McGill Univ, Schulich Sch Mus, Montreal, PQ, Canada
来源：
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2017), VOL 2 | 2017年
关键词：
Optical Music Recognition; Recurrent Neural Network; Long Short-Term Memory;
D O I：
10.1109/ICDAR.2017.260
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Optical Music Recognition is the task of transcribing a music score into a machine readable format. Many music scores are written in a single staff, and therefore, they could be treated as a sequence. Therefore, this work explores the use of Long Short Term Memory (LSTM) Recurrent Neural Networks for reading the music score sequentially, where the LSTM helps in keeping the context. For training, we have used a synthetic dataset of more than 40000 images, labeled at primitive level.
引用
收藏
页码：25 / 26
页数：2
相关论文
共 50 条
12345