首页> 外文会议>IEEE International Conference on Consumer Electronics - Taiwan >Magnitude replacement of real and imaginary modulation spectrum of acoustic spectrograms for noise-robust speech recognition
【24h】

Magnitude replacement of real and imaginary modulation spectrum of acoustic spectrograms for noise-robust speech recognition

机译:噪声稳健语音识别声学谱图的真实和虚构调制谱的级别替代

获取原文

摘要

In this paper, a novel method is proposed to enhance the complex-valued acoustic spectrograms of speech signals via replacing the magnitude part of the corresponding modulation spectrum in order to create noise-robust feature representation for recognition. All the evaluation experiments implemented on the Aurora-2 digit database and task show that the presented method performs better than the baseline MFCC and several well-known noise-robust techniques. These results apparently reveal that this novel method alleviates the effect of noise in speech features significantly.
机译:本文提出了一种新方法,以通过替换相应调制频谱的幅度部分来增强语音信号的复值声学谱图,以便为识别产生噪声鲁棒特征表示。在Aurora-2数字数据库和任务上实现的所有评估实验表明,所提出的方法比基线MFCC和几种众所周知的噪声稳健技术更好。这些结果显然揭示了这种新方法可显着减轻噪音在语音特征中的影响。

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