首页> 外文期刊>Canadian acoustics >A CEPSTRAL-DOMAIN ALGORITHM FOR PITCH ESTIMATION FROM NOISE-CORRUPTED SPEECH
【24h】

A CEPSTRAL-DOMAIN ALGORITHM FOR PITCH ESTIMATION FROM NOISE-CORRUPTED SPEECH

机译:倒谱域语音估计中的基音算法

获取原文
获取原文并翻译 | 示例
获取外文期刊封面目录资料

摘要

Reliable pitch estimation is one of the most significant problems in speech processing applications since any error in pitch detection has a deleterious effect on system performance. Many applications also need robust pitch estimation from noise-conupted speech. Since noise obscures the periodic structure of speech, the pitch estimation in noise is an intricate task. Even though a large number of pitch estimation algorithms have been disclosed in literature for clean speech, it is rather surprising that only a few algorithms have been proposed for the pitch estimation in the presence of noise [l]-[2].
机译:可靠的音调估计是语音处理应用程序中最重要的问题之一,因为音调检测中的任何错误都会对系统性能产生有害影响。许多应用程序还需要根据噪声的语音进行鲁棒的音调估计。由于噪声掩盖了语音的周期性结构,因此噪声中的音调估计是一项复杂的任务。即使在文献中已经公开了许多用于干净语音的音调估计算法,但是令人惊讶的是,在噪声[1]-[2]存在的情况下,仅提出了几种算法来进行音调估计。

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