【24h】

An Efficient Algorithm Bangla Speech Separation

机译:一个有效的算法Bangla语音分离

获取原文

摘要

In this paper we present a new word separation algorithm for Real Time Speech i.e., Continuous Bangla Speech Recognition (CBSR). Prosody has great impact on Bangla speech and the algorithm is developed by considering prosodic feature with energy. Task of this algorithm is to separate Bangla speech into words. At first continuous Bangla speech are fed into the system and the word separation algorithm separate speech into isolate words. Performance of the proposed algorithm is compared to the existing algorithms and result shows that 97% word boundaries are correctly detect.
机译:在本文中,我们介绍了一个新的单词分离算法,用于实时语音i.e.,连续Bangla语音识别(CBSR)。韵律对Bangla讲话产生了很大的影响,并且通过考虑具有能量的韵律特征来开发算法。该算法的任务是将Bangla演讲分开为单词。在第一次连续的孟加拉语音中被喂入系统,并将单词分离算法单独发言分开分离单词。将所提出的算法的性能与现有算法进行比较,结果表明97%字边界是正确的检测。

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