• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Minimum Bayes-risk automatic speech recognition.
【24h】

Minimum Bayes-risk automatic speech recognition.

机译：最低贝叶斯风险自动语音识别。

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

Automatic speech recognition (ASR) systems find use in diverse tasks such as human to machine dialogue, language acquisition by non-native speakers, indexing and retrieval of multi-lingual audio information, and even assistance to individuals with speech impairment. In observing the variety of applications to which ASR is put, the question arises whether a uniform ASR architecture is equally useful for all scenarios. It may be possible to improve application specific performance of the ASR systems by adopting a framework that allows construction of task dependent recognizers. It is the pursuit of this hypothesis that we present in this dissertation.; We first argue that the conventional ASR systems that minimize expected sentence error rate are suboptimal for many tasks of interest. We then describe the framework of minimum Bayes-risk (MBR) classification. A prefix tree based multi-stack A-star search algorithm on recognition lattices is described to implement the MBR recognizers. We provide experimental results showing that the MBR recognizers yield better recognition accuracy than the conventional maximum a-posteriori probability (MAP) recognizer in ASR tasks of word transcription, identification of keywords, and named entity extraction. We also provide experimental results for the task of gene identification from genomic DNA to demonstrate the applicability of MBR classifiers to non-ASR tasks.; To simplify the implementation of the MBR recognizers, a segmental MBR classification scheme is presented. It decomposes a complex MBR recognizer into a sequence of simple recognizers by segmenting the recognition lattice or N-best lists. An interesting outcome of segmental MBR formulation is the derivation of ROVER and other voting techniques as its special cases. Our analysis shows inherent limitations of these voting procedures due to their implicit approximations and assumptions. To alleviate some of these limitations, we present two new procedures derived under the segmental MBR framework.; One of the shortcomings of our implementation of the MBR decoders is the requirement of a lattice or an N-best list, which in turn requires a recognition pass before we could implement MBR decoders. We present our preliminary formulations towards a first pass MBR recognition strategy which processes acoustic data directly. We also discuss extensions of minimum classification error training and other discriminative training methods in the segmental MBR framework.
机译：自动语音识别（ASR）系统可用于多种任务，例如人机对话，非母语使用者的语言习得，多语言音频信息的索引和检索，甚至可以帮助有语言障碍的人。在观察放置ASR的各种应用程序时，会出现一个问题，即统一的ASR体系结构是否对所有情况都同样有用。通过采用允许构造依赖于任务的识别器的框架，有可能改善ASR系统的特定于应用程序的性能。我们在本文中提出的就是对这一假设的追求。我们首先认为，将预期的句子错误率最小化的常规ASR系统对于许多感兴趣的任务而言不是最佳的。然后，我们描述最小贝叶斯风险（MBR）分类的框架。描述了一种基于前缀树的基于识别树的多栈A-star搜索算法来实现MBR识别器。我们提供的实验结果表明，在单词转录，关键字识别和命名实体提取的ASR任务中，MBR识别器比常规的最大后验概率（MAP）识别器产生更好的识别精度。我们还提供了从基因组DNA进行基因鉴定的实验结果，以证明MBR分类器对非ASR任务的适用性。为了简化MBR识别器的实现，提出了分段MBR分类方案。通过分割识别格或N个最佳列表，它将复杂的MBR识别器分解为一系列简单的识别器。分段MBR公式的一个有趣结果是ROVER和其他表决技术作为其特殊情况的派生。我们的分析表明，由于这些投票程序的隐式近似值和假设，它们固有的局限性。为了减轻其中的一些局限性，我们提出了在分段MBR框架下派生的两个新过程。我们实现MBR解码器的缺点之一是需要晶格或N最佳列表，这又要求在实现MBR解码器之前需要通过识别。我们介绍了我们的初步配方，旨在通过MBR识别策略直接处理声学数据。我们还将讨论分段MBR框架中最小分类错误训练和其他判别训练方法的扩展。

著录项

  • 作者

    Goel, Vaibhava.;

  • 作者单位

    The Johns Hopkins University.;

  • 授予单位 The Johns Hopkins University.;
  • 学科 Computer Science.; Engineering Biomedical.
  • 学位 Ph.D.
  • 年度 2001
  • 页码 124 p.
  • 总页数 124
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 自动化技术、计算机技术;生物医学工程;
  • 关键词

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