• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Proceedings of the speech recognition workshop >THE 1996 BBN BYBLOS HUB-4 TRANSCRIPTION SYSTEM
【24h】

THE 1996 BBN BYBLOS HUB-4 TRANSCRIPTION SYSTEM

机译：1996年BBN BYBLOS HUB-4转录系统

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

In this paper, we describe the BBN Byblos system used for the 1996 Hub-4 Partitioned Evaluation (PE) and Unparti-tioned Evaluation (UE) tests. For the PE, we chose to ignore the segment feature labels that were given to the system as side-information so that our approach would generalize trivially to the UE. Moreover, we chose not to model specific channel conditions in the training because the observed gains were too small to warrant the additional system complexity required to support them. In the end, we estimated a single set of acoustic models from only 40 hours of broadcast news data. For the UE, the data was automatically segmented with a simple dual-gender phoneme recognizer that efficiently located pauses and changes in speakers' gender. After this preliminary stage of segmentation and gender-classification, our UE and PE systems were identical. We achieved a 30.2% word error rate on the PE test and 31.8% on the UE test -only a 5% relative degradation from our PE result.
机译：在本文中，我们描述了用于1996年Hub-4分区评估（PE）和未分区评估（UE）测试的BBN Byblos系统。对于PE，我们选择忽略作为辅助信息提供给系统的分段特征标签，以便我们的方法可以简单地推广到UE。此外，我们选择不对训练中的特定信道条件建模，因为观察到的增益太小，无法保证支持它们所需的额外系统复杂性。最后，我们仅从40个小时的广播新闻数据中估计出一套声学模型。对于UE，数据可以通过简单的双性别音素识别器自动分段，该识别器可以有效地定位说话者性别的停顿和变化。经过细分和性别分类的初步阶段之后，我们的UE和PE系统完全相同。在PE测试中，我们达到了30.2％的字错误率，在UE测试中，达到了31.8％-仅比我们的PE结果降低了5％。

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