...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of signal processing systems for signal, image, and video technology >Basis-Based Speaker Adaptation Using Partitioned HMM Mean Parameters of Training Speaker Models
【24h】

Basis-Based Speaker Adaptation Using Partitioned HMM Mean Parameters of Training Speaker Models

机译：基于分区HMM均值参数的训练说话者模型的基于说话人的自适应

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 presents the basis-based speaker adaptation method that includes approaches using principal component analysis (PCA) and two-dimensional PCA (2DPCA). The proposed method partitions the hidden Markov model (HMM) mean vectors of training models into subvectors of smaller dimension. Consequently, the sample covariance matrix computed using the partitioned HMM mean vectors has various dimensions according to the dimension of the subvectors. From the eigen-decomposition of the sample covariance matrix, basis vectors are constructed. Thus, the dimension of basis vectors varies according to the dimension of the sample covariance matrix, and the proposed method includes PCA and 2DPCA-based approaches. We present the adaptation equation in both the maximum likelihood (ML) and maximum a posteriori (MAP) frameworks. We perform continuous speech recognition experiments using the Wall Street Journal (WSJ) corpus. The results show that the model with basis vectors whose dimensions are between those of PCA and 2DPCA-based approaches shows good overall performance. The proposed approach in the MAP framework shows additional performance improvement over the ML counterpart when the number of adaptation parameters is large but the amount of available adaptation data is small. Furthermore, the performance of the approach in the MAP framework approach is less sensitive to the choice of model order than the ML counterpart.
机译：本文介绍了基于基础的说话人自适应方法，其中包括使用主成分分析（PCA）和二维PCA（2DPCA）的方法。该方法将训练模型的隐马尔可夫模型（HMM）均值向量划分为较小维的子向量。因此，根据子向量的维数，使用划分后的HMM平均向量计算的样本协方差矩阵具有不同的维数。根据样本协方差矩阵的特征分解，构建基向量。因此，基向量的维数根据样本协方差矩阵的维数而变化，并且所提出的方法包括基于PCA和2DPCA的方法。我们在最大似然（ML）和最大后验（MAP）框架中提出了适应方程。我们使用《华尔街日报》（WSJ）语料库进行连续的语音识别实验。结果表明，具有基本向量且维数在PCA和基于2DPCA的方法之间的模型具有良好的整体性能。当自适应参数的数量大而可用自适应数据的数量少时，MAP框架中提出的方法显示出比ML对应方法更好的性能。此外，与ML对应方法相比，MAP框架方法中方法的性能对模型顺序的选择不太敏感。

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