Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition
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 addi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Journal of Robotics |
| Online Access: | http://dx.doi.org/10.1155/2017/2061827 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558168734957568 |
|---|---|
| author | YuKang Jia Zhicheng Wu Yanyan Xu Dengfeng Ke Kaile Su |
| author_facet | YuKang Jia Zhicheng Wu Yanyan Xu Dengfeng Ke Kaile Su |
| author_sort | YuKang Jia |
| collection | DOAJ |
| description | 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%. 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. |
| format | Article |
| id | doaj-art-3f7f4aae1614493a9b6855b0bdf4eb0a |
| institution | Kabale University |
| issn | 1687-9600 1687-9619 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Robotics |
| spelling | doaj-art-3f7f4aae1614493a9b6855b0bdf4eb0a2025-02-03T01:33:06ZengWileyJournal of Robotics1687-96001687-96192017-01-01201710.1155/2017/20618272061827Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note RecognitionYuKang Jia0Zhicheng Wu1Yanyan Xu2Dengfeng Ke3Kaile Su4School of Information Science and Technology, Beijing Forestry University, No. 35 Qinghuadong Road, Haidian District, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, No. 35 Qinghuadong Road, Haidian District, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, No. 35 Qinghuadong Road, Haidian District, Beijing 100083, ChinaNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 Zhongguancundong Road, Haidian District, Beijing 100190, ChinaCollege of Information Science and Technology, Jinan University, No. 601, West Huangpu Avenue, Guangzhou, Guangdong 510632, ChinaLong 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%. 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.http://dx.doi.org/10.1155/2017/2061827 |
| spellingShingle | YuKang Jia Zhicheng Wu Yanyan Xu Dengfeng Ke Kaile Su Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition Journal of Robotics |
| title | Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition |
| title_full | Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition |
| title_fullStr | Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition |
| title_full_unstemmed | Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition |
| title_short | Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition |
| title_sort | long short term memory projection recurrent neural network architectures for piano s continuous note recognition |
| url | http://dx.doi.org/10.1155/2017/2061827 |
| work_keys_str_mv | AT yukangjia longshorttermmemoryprojectionrecurrentneuralnetworkarchitecturesforpianoscontinuousnoterecognition AT zhichengwu longshorttermmemoryprojectionrecurrentneuralnetworkarchitecturesforpianoscontinuousnoterecognition AT yanyanxu longshorttermmemoryprojectionrecurrentneuralnetworkarchitecturesforpianoscontinuousnoterecognition AT dengfengke longshorttermmemoryprojectionrecurrentneuralnetworkarchitecturesforpianoscontinuousnoterecognition AT kailesu longshorttermmemoryprojectionrecurrentneuralnetworkarchitecturesforpianoscontinuousnoterecognition |