...
首页> 外文期刊>International Journal of Innovative Computing Information and Control >ROBUST SPEECH PERCEPTUAL HASHING ALGORITHM BASED ON LINEAR PREDICATION RESIDUAL OF G.729 SPEECH CODEC
【24h】

ROBUST SPEECH PERCEPTUAL HASHING ALGORITHM BASED ON LINEAR PREDICATION RESIDUAL OF G.729 SPEECH CODEC

机译:基于G.729语音编解码器线性预测残差的鲁棒语音感知散列算法

获取原文
获取原文并翻译 | 示例
           

摘要

In this paper, in order to meet the requirements of speech authentication for low amount of data and low complexity in the bandwidth resource-limited speech communication environment, we present a new robust perceptual audio hashing algorithm combined with the G. 729 coding standards. This algorithm extracts the linear prediction residual (LPR) as feature of speech perceptual in the processing of the G. 729 speech codec, and extracts the perceptual hash values. The experimental results illustrate the effectiveness of the proposed algorithm in terms of better robustness and discrimination to common speech transmission operation, low time complexity and high efficiency of the proposed algorithm as well, and it can effectively distinguish between the permissible operating and malicious tampering. In the meantime, it has a higher precision for tamper localization.
机译:为了满足带宽资源有限的语音通信环境中数据量少,复杂度低的要求,本文提出了一种结合G.729编码标准的鲁棒感知音频哈希算法。该算法提取G.729语音编解码器处理过程中作为语音感知特征的线性预测残差(LPR),并提取感知哈希值。实验结果表明,该算法具有较好的鲁棒性和对普通语音传输操作的辨别力,较低的时间复杂度和较高的效率,可以有效区分允许的操作和恶意篡改。同时,它具有更高的篡改定位精度。

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