首页> 外文会议>IEEE International Conference on Consumer Electronics - Taiwan >Voice conversion based on empirical conditional distribution in resource-limited scenarios
【24h】

Voice conversion based on empirical conditional distribution in resource-limited scenarios

机译:资源受限情况下基于经验条件分布的语音转换

获取原文

摘要

In this paper, a computationally efficient voice conversion system has been designed in order to improve the performance in resource-limited scenarios. First, mixtures of Gaussians (MoGs) at fixed locations of Mel frequencies have been used to represent the spectrum of STRAIGHT compactly. Second, the key conditional distributions for prediction are approximated by building histograms of aligned features empirically. Experiments have confirmed that our proposed method can obtain fairly good results compared to the traditional method without huge computational costs.
机译:本文设计了一种计算有效的语音转换系统,以提高资源受限情况下的性能。首先,在梅尔频率固定位置上的高斯(MoGs)混合已被用来紧凑地表示STRAIGHT的频谱。第二,通过建立经验对齐特征的直方图来近似预测的关键条件分布。实验已经证实,与传统方法相比,我们提出的方法可以获得相当好的结果,而没有大量的计算成本。

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