Mapping Acoustic Vector Space and Document Vector Space by RNN-LSTM
Mapping Acoustic Vector Space and Document Vector Space by RNN-LSTM
复制标题
DOI：
10.1109/gcce.2018.8574867
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Ryota Nishimura;Miho Higaki;N. Kitaoka
中科院分区：
文献类型：
--
作者：
Ryota Nishimura;Miho Higaki;N. Kitaoka
在本研究中，我们提出了一种使用深度学习（近年来迅速发展和利用的机器学习算法）在不同媒体之间进行搜索的方法（跨媒体映射）。该网络采用了递归神经网络（RNN）。利用本文提出的方法，可以将音乐和歌词进行关联，并且可以使用文档对音乐进行搜索。通过应用该模型，可以实现一个音乐建议系统，该系统可以监控人与人之间的对话并提供适当的BGM。在本文中，我们构建了提案模型，并进行了评估实验，证实了跨媒体映射的可能性。
In this research, we propose a method of searching between different media (cross-media mapping) using deep learning (Machine learning algorithm which is developed and utilized rapidly in recent years). A recurrent neural network (RNN) is used for the network. By using the proposed method, music and lyrics can be correlated, and music can be searched using documents. By applying this model, it is possible to realize a music suggestion system that monitors human-to-human dialogue and provides appropriate BGM. In this paper, we constructed a proposal model, conducted an evaluation experiment, and confirmed the possibility of cross-media mapping.