...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Acoustics >Voice activity detection with quasi-quadrature filters and GMM decomposition for speech and noise
【24h】

Voice activity detection with quasi-quadrature filters and GMM decomposition for speech and noise

机译：用准正交过滤器和GMM分解进行语音活动检测语音和噪声

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

One of basic algorithms employed in technologies such as automatic speech recognition (ASR) systems is voice activity detection (VAD). Speech contains many pauses, whose interpretation might lead to recognition errors. Scientific literature provides numerous VAD algorithms, though many of them have substantial memory and/or calculation time requirements. On the other hand, the efficacy of those with smaller requirements is usually unsatisfactory. This paper proposes a modification to a single frequency filtering based algorithm known from literature, changing the methods of determining envelopes and the detection threshold. The purpose of these modifications was to reduce the calculation time and memory requirements without losing the efficiency of the algorithm. Also, a completely new algorithm of determining the detection threshold, using the approximation of hypothesis probability distribution was developed. The obtained results are satisfactory. (C) 2020 The Authors. Published by Elsevier Ltd.
机译：自动语音识别（ASR）系统等技术中使用的基本算法之一是语音活动检测（VAD）。语音包含许多暂停，其解释可能导致识别错误。科学文献提供了众多VAD算法，尽管它们中的许多都具有大量的存储器和/或计算时间要求。另一方面，要求较小的人的功效通常是不令人满意的。本文提出了一种从文献中已知的基于单频滤波的算法的修改，改变了确定信封的方法和检测阈值。这些修改的目的是减少计算时间和内存要求，而不会失去算法的效率。此外，开发了使用假设概率分布的近似来确定检测阈值的全新算法。获得的结果令人满意。 （c）2020作者。 elsevier有限公司出版

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