首页> 外文会议>Proceedings of the speech recognition workshop >OVERVIEW OF THE 1997 DARPA SPEECH RECOGNITION WORKSHOP
【24h】

OVERVIEW OF THE 1997 DARPA SPEECH RECOGNITION WORKSHOP

机译:1997年DARPA语音识别研讨会概述

获取原文
获取原文并翻译 | 示例

摘要

This year's DARPA Speech Recognition Workshop focussed on one multi-faceted technical challenge-recognizing the "found speech" in radio and television news broadcasts. As such, this challenge is an expansion of last year's Hub 4 Broadcast News Benchmark Tests.rnThis year's Hub 4 Broadcast News tests made trial use of a new paradigm-a "Partitioned Evaluation" (PE), which was intended to contrast with an "Unpartitioned Evaluation" (UE), and which made use of information derived from extensively annotated and time-marked reference transcriptions which in some cases obviated the need for "chopping" or segmentation modules as components in the Hub 4 systems.
机译:今年的DARPA语音识别研讨会的重点是一个多方面的技术挑战-识别广播和电视新闻广播中的“发现的语音”。因此,这项挑战是对去年的Hub 4广播新闻基准测试的扩展。rn今年的Hub 4广播新闻测试采用了一种新的范式-“分区评估”(PE),旨在与“ “未分区评估”(UE),它使用了从带有大量注释和时间标记的参考转录中获得的信息,在某些情况下,无需在中心4系统中将“斩波”或细分模块作为组件。

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