Unsupervised acoustic model adaptation based on phoneme error minimization
Unsupervised acoustic model adaptation based on phoneme error minimization
复制标题
基于音素误差最小化的无监督声学模型自适应
DOI：
10.21437/icslp.2002-67
复制
发表时间：
2002
影响因子：
20.6
通讯作者：
Y. Ariki
中科院分区：
文献类型：
--
作者：
J. Ogata;Y. Ariki
本文提出了一种新的无监督声学模型自适应译码方法。在无监督的适应框架中，标签的错误识别极大地影响了适应过程的有效性。因此，在无监督自适应中，以置信度度量为指导的自适应数据的选择是有效的。我们提出了精确音素标签的音素错误最小化框架，并使用音素级置信度措施来改进无监督适应。实验结果表明，该方法可以减少自适应过程中的误识别标签，从而提高自适应精度。进一步验证了该方法在迭代无监督自适应框架下的有效性。
In this paper, a new decoding method for unsupervised acoustic model adaptation is presented. In unsupervised adaptation framework, the effectiveness of adaptation process is greatly affected by the mis-recognized labels. Therefore, selection of the adaptation data guided by the confi-dence measures is effective in unsupervised adaptation. We propose phoneme error minimization framework for exact phoneme labels and use of phoneme-level confidence measures for improved unsupervised adaptation. Experimental results showed that the proposed method could reduce the mis-recognized labels in the adaptation process, and consequently improved the adaptation accuracy. Furthermore, it was confirmed that the proposed method is effective in an iterative unsupervised adaptation framework.