• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Communications vol.1; 20040603-05; Bucharest(RO) >HMM INITIALIZATION AND TRAINING FOR A ROMANIAN LANGUAGE CONTINUOUS SPEECH RECOGNIZER
【24h】

HMM INITIALIZATION AND TRAINING FOR A ROMANIAN LANGUAGE CONTINUOUS SPEECH RECOGNIZER

机译：罗马尼亚语连续语音识别器的HMM初始化和培训

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

This paper is about training of acoustical models in continuous speech recognition framework. It is known that the performance of an automatic speech recognition (ASR) system depends on how accurate it models the speech. In modeling phone-based HMM, the training stage is critical for the system accuracv. We have focused on HMM parameter initialization and re-estimation of these parameters by embedded training. There are two methods presented herein for initialization: the first one is based on segmented training data while the other one makes all the models identical in the so called flat start scheme. After models initialization, some aspects about embedded training are considered. Finally, experimental results with two gender dependent systems are tested with the two methods. We concluded that hand-labeled data is not necessary for training HMM, flat start being a more practical solution to model initialization.
机译：本文是关于在连续语音识别框架中训练声学模型的。众所周知，自动语音识别（ASR）系统的性能取决于其对语音建模的准确性。在基于电话的HMM建模中，培训阶段对于系统准确度至关重要。我们专注于HMM参数初始化和通过嵌入式训练对这些参数的重新估计。本文提供了两种初始化方法：第一种基于分段训练数据，而另一种则使所有模型在所谓的平稳启动方案中相同。在模型初始化之后，将考虑有关嵌入式训练的某些方面。最后，使用两种方法测试了两种性别相关系统的实验结果。我们得出的结论是，手工标记的数据对于训练HMM并不是必需的，而平稳启动是模型初始化的更实用的解决方案。

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