• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2016 IEEE International Workshop on Acoustic Signal Enhancement >Oracle performance investigation of the ideal masks
【24h】

Oracle performance investigation of the ideal masks

机译：Oracle性能调查的理想口罩

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

Various ideal masks have been used as the training targets for supervised speech separation. While different choices often lead to different results, the reason remains unclear. In this paper, an oracle method is applied to investigate the properties of the ideal masks including the ideal binary mask (IBM), the ideal ratio mask (IRM), the phase sensitive mask (PSM) and the complex ideal ratio maks (cIRM). They are evaluated in terms of intelligibility and quality under a general speech separation scenario. The relative importance of phase is also taken into consideration. Moreover, we introduce a novel ideal gain mask (IGM) which performs generally better than IRM and one alternative of the cIRM. It is shown that the masks are not equally designed and the results provide a strong reference to the potential performance of supervised algorithms.
机译：各种理想的口罩已被用作监督语音分离的训练目标。尽管不同的选择通常会导致不同的结果，但原因尚不清楚。本文采用一种oracle方法来研究理想掩模的特性，包括理想二进制掩模（IBM），理想比率掩模（IRM），相敏掩模（PSM）和复杂理想比率麦克斯（cIRM） 。在一般语音分离场景下，根据清晰度和质量对它们进行评估。还考虑了阶段的相对重要性。此外，我们介绍了一种新型的理想增益掩模（IGM），其性能通常优于IRM和cIRM的一种替代方案。结果表明，掩膜设计不均，结果为监督算法的潜在性能提供了强有力的参考。

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