首页> 外文会议>Proceedings of the speech recognition workshop >Some Results on Search Complexity vs Accuracy
【24h】

Some Results on Search Complexity vs Accuracy

机译:关于搜索复杂性与准确性的一些结果

获取原文
获取原文并翻译 | 示例

摘要

This paper presents three different techniques applied in or developed during the 1996 Hub-4 broadcast news transcription task. First, an efficient shortest path graph search algorithm is applied to the word lattice created by Viterbi search, producing a globally optimum result. This reduces the word error rate by about 3-10% (relative), depending on the test set. The execution time is at or close to real time for most utterances. Second, a segmented N-best list generation algorithm is described for producing compact N-best lists for very long utterances. Finally, a temporal smoothing technique is compared to deleted interpolation. On one test set, temporal smoothing reduces the error rate by 3% for an 8% increase in search cost, while the latter improves by 6% for a 50% increase in search cost.
机译:本文介绍了在1996年Hub-4广播新闻转录任务中应用或开发的三种不同技术。首先,将有效的最短路径图搜索算法应用于维特比搜索创建的单词晶格,从而产生全局最优结果。根据测试集,这可以将字错误率降低约3-10%(相对)。对于大多数话语,执行时间等于或接近实时。其次,描述了分段的N个最佳列表生成算法,用于产生非常长的发声的紧凑的N个最佳列表。最后,将时间平滑技术与删除的插值进行比较。在一个测试集上,时间平滑将错误率降低了3%,搜索成本增加了8%,而后者则提高了6%,搜索成本增加了50%。

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