Name
Abstract | ||
|---|---|---|
With the rapid development of the internet, recent years has witnessed an express development of artificial intelligence. At present, the deep learning method represented by the long short-term memory (LSTM) network is gradually being studied and applied to the conversion model. However, there is no enough research on the current braille music. This paper uses LSTM network for braille music segmentation research. The conversion of braille music needs to use conversion model to describe and realize equivalent conversion. First, construct a braille music corpus: we analyze the composition rules of braille music symbols, and then study the braille music word segmentation corpus, thus a braille music corpus is manually constructed by using the existing braille music materials. Secondly, construct a braille music participle model: in this paper, we use the framework of in-depth learning to construct a braille music word segmentation model. Finally, multiple iterations of training are performed by using the braille music participle model. Multiple iterations of training can enable the machine to automatically learn the combination rules of braille music in the corpus. Through the experiment, it is found that braille music segmentation based on LSTM network has achieved an expected effect, which lays a foundation for further achieving the conversion of braille music. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/FSKD.2018.8687136 | ICNC-FSKD |
Field | DocType | Citations |
Participle,Computer science,Segmentation,Long short term memory,Text segmentation,Natural language processing,Artificial intelligence,Deep learning,Braille,Machine learning,The Internet | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wenfeng Wu | 1 | 0 | 0.68 |
| Biao Liu | 2 | 1 | 3.39 |
| Wei Su | 3 | 0 | 0.68 |
| He Lin | 4 | 2 | 1.78 |