• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2002 6th International Conference on Signal Processing Proceedings (ICSP'02) Vol.1; Aug 26-30, 2002; Beijing, China >Optimizing Speech Enhancement Based on Noise Masked Probability
【24h】

Optimizing Speech Enhancement Based on Noise Masked Probability

机译：基于噪声掩盖概率的语音增强优化

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

An optimal approach for enhancing a speech signal degraded by uncorrelated stationary additive noise, which exploits auditory perception properties, is proposed. Based on auditory masking effects, the speech spectra estimate is performed in two cases: noisy speech spectra for noise masked and classical spectral subtraction estimate for noise unmasked. Taking into account the uncertainty of the noise presence, the enhanced speech signal spectra are obtained by a weighted sum of these two estimates, where the weights are given by the noise masked probability. The performance of the proposed speech enhancement approach has been evaluated with speech distortion and informal listening tests. Comparing with Azirani's method and MMSE-STSA estimator, results show that the speech distortion has been decreased apparently and the musical noise has been suppressed.
机译：提出了一种利用听觉感知特性来增强由不相关的平稳加性噪声引起的语音信号降级的最佳方法。基于听觉掩蔽效应，在两种情况下执行语音频谱估计：用于掩蔽噪声的嘈杂语音频谱和用于未掩蔽噪声的经典频谱减法估计。考虑到噪声存在的不确定性，通过这两个估计的加权和获得增强的语音信号频谱，其中权重由噪声掩盖概率给出。所提出的语音增强方法的性能已通过语音失真和非正式聆听测试进行了评估。与Azirani的方法和MMSE-STSA估计器相比，结果表明，语音失真明显降低，音乐噪声得到了抑制。

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