...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Speech and Audio Proceessing >Segmental minimum Bayes-risk decoding for automatic speech recognition
【24h】

Segmental minimum Bayes-risk decoding for automatic speech recognition

机译：分段最小贝叶斯风险解码，用于自动语音识别

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

Minimum Bayes-risk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum a-posteriori probability (MAP) decoders through N-best list rescoring and A* search over word lattices. We present a segmental minimum Bayes-risk decoding (SMBR) framework that simplifies the implementation of MBR recognizers through the segmentation of the N-best lists or lattices over which the recognition is to be performed. This paper presents lattice cutting procedures that underly SMBR decoding. Two of these procedures are based on a risk minimization criterion while a third one is guided by word-level confidence scores. In conjunction with SMBR decoding, these lattice segmentation procedures give consistent improvements in recognition word error rate (WER) on the Switchboard corpus. We also discuss an application of risk-based lattice cutting to multiple-system SMBR decoding and show that it is related to other system combination techniques such as ROVER. This strategy combines lattices produced from multiple ASR systems and is found to give WER improvements in a Switchboard evaluation system.
机译：最小贝叶斯（MBR）语音识别器已被证明可以通过N个最佳列表记录和单词格上的A *搜索来改善传统的最大后验概率（MAP）解码器。我们提出了分段最小贝叶斯风险解码（SMBR）框架，该框架通过对要进行识别的N个最佳列表或网格进行分段，简化了MBR识别器的实现。本文介绍了基于SMBR解码的晶格切割程序。这些程序中的两种基于风险最小化标准，而第三种则以单词级别的置信度分数为指导。结合SMBR解码，这些晶格分割过程可在交换台语料库上对识别词错误率（WER）进行持续改进。我们还将讨论基于风险的网格切割在多系统SMBR解码中的应用，并表明它与其他系统组合技术（例如ROVER）有关。这种策略结合了由多个ASR系统产生的晶格，并发现可以在配电盘评估系统中改善WER。

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