• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE Automatic Speech Recognition and Understanding Workshop >An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription
【24h】

An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription

机译：关于提高Chime-5晚宴聚会转录的ASR培训和测试的有效性的调查

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available. However, there has been a longstanding debate whether enhancement should also be carried out on the ASR training data. In an extensive experimental evaluation on the acoustically very challenging CHiME-5 dinner party data we show that: (i) cleaning up the training data can lead to substantial error rate reductions, and (ii) enhancement in training is advisable as long as enhancement in test is at least as strong as in training. This approach stands in contrast and delivers larger gains than the common strategy reported in the literature to augment the training database with additional artificially degraded speech. Together with an acoustic model topology consisting of initial CNN layers followed by factorized TDNN layers we achieve with 41.6 % and 43.2 % WER on the DEV and EVAL test sets, respectively, a new single-system state-of-the-art result on the CHiME-5 data. This is a 8 % relative improvement compared to the best word error rate published so far for a speech recognizer without system combination.
机译：尽管神经网络声学模型具有强大的建模能力，但如果有多通道数据可用，语音增强功能将显示出额外的单词错误率改善。但是，关于是否也应在ASR培训数据上进行增强，一直存在着长期的争论。在对声学上非常具有挑战性的CHiME-5晚餐聚会数据进行的广泛实验评估中，我们表明：（i）清理训练数据可以大大降低错误率，并且（ii）增强训练水平是可取的。测试至少和训练中一样强大。与文献中报道的用额外的人工降级语音来增强训练数据库的常用策略相比，该方法形成了鲜明的对比，并提供了更大的收益。结合由最初的CNN层和分解的TDNN层组成的声学模型拓扑，我们在DEV和EVAL测试集上分别获得了41.6％和43.2％的WER，从而获得了最新的单系统最新结果。 CHiME-5数据。与迄今为止针对没有系统组合的语音识别器发布的最佳单词错误率相比，这是8％的相对改进。

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