首页> 外文会议>International Symposium on Intelligent Multimedia, Video and Speech Processing >Efficient decoding algorithms for mandarin connected digit speech recognition
【24h】

Efficient decoding algorithms for mandarin connected digit speech recognition

机译:高效解码算法,用于普通话连接数字语音识别

获取原文

摘要

In this paper, a set of efficient decoding algorithms based on a Speaker Independent Mandarin Connected Digit Speech Recognition System is proposed. By simplifying the computation of observation probabilities and adopting improved beam search pruning algorithm combined with duration information, the average decoding time is reduced from 0.92 second to 0.11 second per digit string while the recognition rate of ukkhown4ength string is only decreased from 94.3% to 94.0%.
机译:在本文中,提出了一组基于扬声器独立普通话连接数字语音识别系统的高效解码算法。通过简化观察概率的计算和采用改进的光束搜索修剪算法与持续时间信息结合,平均解码时间从0.92秒减小到0.11秒秒,而Ukkhown4长度串的识别率仅从94.3%降低到94.0% 。

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