• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on audio, speech and language processing >A global, boundary-centric framework for unit selection text-to-speech synthesis
【24h】

A global, boundary-centric framework for unit selection text-to-speech synthesis

机译：用于单元选择文本到语音合成的全局边界中心框架

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The level of quality that can be achieved by modern concatenative text-to-speech synthesis heavily depends on the optimization criteria used in the unit selection process. While effective cost functions arise naturally for prosody assessment, the criteria typically selected to quantify discontinuities in the speech signal do not closely reflect users' perception of the resulting acoustic waveform. This paper introduces an alternative feature extraction paradigm, which eschews general purpose Fourier analysis in favor of a modal decomposition separately optimized for each boundary region. The ensuing transform framework preserves, by construction, those properties of the waveform which are globally relevant to each concatenation considered. In addition, it leads to a novel discontinuity measure which jointly, albeit implicitly, accounts for both interframe incoherence and discrepancies in formant frequencies/bandwidths. Experimental evaluations are conducted to characterize the behavior of this new metric, first on a contiguity prediction task, and then via a systematic listening comparison using a conventional metric as baseline. The results underscore the viability of the proposed framework in quantifying the perception of discontinuity between acoustic units.
机译：现代的串联文本到语音合成所能达到的质量水平在很大程度上取决于单元选择过程中使用的优化标准。虽然有效的成本函数自然会出现在韵律评估中，但是通常用来量化语音信号中的不连续性的标准并不能紧密反映用户对所得声波形的感知。本文介绍了一种替代性特征提取范例，该方法避免了通用傅立叶分析，而采用了针对每个边界区域分别优化的模态分解。随后的变换框架通过构造保留了与所考虑的每个串联全局相关的波形属性。另外，这导致了一种新颖的不连续性度量，尽管隐含地共同解决了帧间不连贯性和共振峰频率/带宽的差异。进行实验评估以表征此新指标的行为，首先是在连续性预测任务上，然后是使用常规指标作为基线的系统聆听比较。结果强调了拟议框架在量化声学单元之间不连续感方面的可行性。

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