...
首页> 外文期刊>Eurasip Journal on Wireless Communications and Networking >Improved Wasserstein conditional generative adversarial network speech enhancement
【24h】

Improved Wasserstein conditional generative adversarial network speech enhancement

机译:改进的Wasserstein有条件生成的对抗网络语音增强

获取原文
获取原文并翻译 | 示例
           

摘要

The speech enhancement based on the generative adversarial network has achieved excellent results with large quantities of data, but performance in the low-data regime and tasks like unseen data learning still lag behind. In this work, we model Wasserstein Conditional Generative Adversarial Network-Gradient Penalty speech enhancement system and introduce the elastic network into the objective function to simplify and improve the performance of the model in low-resource data environment. We argue that the regularization is significant in learning with small amounts of data and the available information of the input data is key in speech enhancement performance and generalization ability of the model, which means that network parameters and network structure can be set up and designed according to the characteristics of actual input data. Experiments on the noisy speech corpus show that the improved algorithm outperforms previous generative adversarial network speech enhancement approach.
机译:基于生成的对策网络的语音增强已经实现了具有大量数据的优异结果,但低数据制度和任务中的性能,如未知数据学习仍然滞后。在这项工作中,我们模拟了Wassersein条件生成的对抗性网络梯度惩罚语音增强系统,并将弹性网络引入目标函数,以简化和提高低资源数据环境中模型的性能。我们认为,使用少量数据学习的正规化是显着的,并且输入数据的可用信息是语音增强性能和模型的泛化能力的关键,这意味着可以根据网络参数和网络结构设置和设计到实际输入数据的特征。嘈杂的语音语料库的实验表明,改进的算法优于先前的生成对抗网络语音增强方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号