Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano's Continuous Note Recognition

	Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano's Continuous Note Recognition
	YuKang Jia,; Zhicheng Wu; Yanyan Xu; Dengfeng Ke; Dengfeng Ke
发表期刊	Journal of Robotics
	2017
期号	0 页码:1-7
摘要	Long Short-TermMemory (LSTM) is a kind of Recurrent Neural Networks (RNN) relating to time series, which has achieved good performance in speech recogniton and image recognition. Long Short-Term Memory Projection (LSTMP) is a variant of LSTM to further optimize speed and performance of LSTM by adding a projection layer. As LSTM and LSTMP have performed well in pattern recognition, in this paper, we combine them with Connectionist Temporal Classification (CTC) to study piano’s continuous note recognition for robotics. Based on the Beijing Forestry University music library, we conduct experiments to show recognition rates and numbers of iterations of LSTM with a single layer, LSTMP with a single layer, and Deep LSTM (DLSTM, LSTM with multilayers). As a result, the single layer LSTMP proves performing much better than the single layer LSTM in both time and the recognition rate; that is, LSTMP has fewer parameters and therefore reduces the training time, and, moreover, benefiting from the projection layer, LSTMP has better performance, too.The best recognition rate of LSTMP is 99.8%. As for DLSTM, the recognition rate can reach 100% because of the effectiveness of the deep structure, but compared with the single layer LSTMP, DLSTM needs more training time.
关键词	Speech Recogniton 、 Image Recognition
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40810
专题	多模态人工智能系统全国重点实验室_智能交互
推荐引用方式 GB/T 7714	YuKang Jia,,Zhicheng Wu,Yanyan Xu,et al. Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano's Continuous Note Recognition[J]. Journal of Robotics,2017(0):1-7.
APA	YuKang Jia,,Zhicheng Wu,Yanyan Xu,Dengfeng Ke,&Dengfeng Ke.(2017).Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano's Continuous Note Recognition.Journal of Robotics(0),1-7.
MLA	YuKang Jia,,et al."Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano's Continuous Note Recognition".Journal of Robotics .0(2017):1-7.