TY - JOUR A2 - 渡边圭吾AU - 佳裕康AU - 吴，志成盟 - 徐岩岩AU - 柯，登封AU - 苏，凯乐PY - 2017年DA - 2017年9月12日TI - 长短期记忆Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition SP - 2061827 VL - 2017 AB - Long Short-Term Memory (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 ％ 。至于DLSTM，识别率可以达到 100 ％ 因为深层结构的有效性，但与单层相比LSTMP，DLSTM需要更多的训练时间。SN - 1687-9600 UR - https://doi.org/10.1155/2017/2061827 DO - 10.1155 /二百○六万一千八百二十七分之二千○一十七JF - 中华机器人PB的 - Hindawi出版KW - ER -