首页> 外文期刊>Audio, Speech, and Language Processing, IEEE Transactions on >Investigations on an EM-Style Optimization Algorithm for Discriminative Training of HMMs
【24h】

Investigations on an EM-Style Optimization Algorithm for Discriminative Training of HMMs

机译:EM风格优化算法的HMM判别训练研究

获取原文
获取原文并翻译 | 示例

摘要

Today's speech recognition systems are based on hidden Markov models (HMMs) with Gaussian mixture models whose parameters are estimated using a discriminative training criterion such as Maximum Mutual Information (MMI) or Minimum Phone Error (MPE). Currently, the optimization is almost always done with (empirical variants of) Extended Baum-Welch (EBW). This type of optimization requires sophisticated update schemes for the step sizes and a considerable amount of parameter tuning, and only little is known about its convergence behavior. In this paper, we derive an EM-style algorithm for discriminative training of HMMs. Like Expectation-Maximization (EM) for the generative training of HMMs, the proposed algorithm improves the training criterion on each iteration, converges to a local optimum, and is completely parameter-free. We investigate the feasibility of the proposed EM-style algorithm for discriminative training of two tasks, namely grapheme-to-phoneme conversion and spoken digit string recognition.
机译:当今的语音识别系统基于具有高斯混合模型的隐马尔可夫模型(HMM),其参数是使用诸如最大互信息(MMI)或最小电话错误(MPE)之类的判别训练准则来估计的。当前,优化几乎总是使用扩展Baum-Welch(EBW)(的经验变体)完成的。这种类型的优化要求针对步长和复杂的参数调整进行复杂的更新,并且对其收敛行为知之甚少。在本文中,我们推导了一种EM风格的HMM判别训练算法。像用于HMM生成训练的期望最大化(EM)一样,该算法改进了每次迭代的训练准则,收敛到局部最优,并且完全没有参数。我们调查提出的EM风格算法对两个任务(字素到音素转换和语音数字字符串识别)进行判别训练的可行性。

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