Bayesian adaptation and adaptively trained systems
Bayesian adaptation and adaptively trained systems
复制标题
DOI：
10.1109/asru.2005.1566532
复制
发表时间：
2005-12
期刊：
影响因子：
--
通讯作者：
K. Yu;M. Gales
中科院分区：
文献类型：
--
作者：
K. Yu;M. Gales
随着使用FOUND数据的增加，正在使用自适应训练建立更多的系统。这里，变换被用来表示不需要的声学可变性，例如说话者和声学环境的变化，从而允许仅对语音的“纯”可变性建模的规范模型被训练。自适应训练可以在贝叶斯框架内描述。通过使用复杂性控制方法来确保稳健的参数估计，标准点估计自适应训练可以在该贝叶斯框架内被证明是合理的。然而，在识别过程中，通常无法控制可用的数据量。因此，最好能够在识别过程中使用完整的贝叶斯方法来应用变换，而不是使用标准点估计。本文讨论了贝叶斯方法的各种逼近，包括一种新的变分贝叶斯逼近。然后描述了这些方法在使用CAT和MLLR变换的最先进的自适应训练系统中的应用，并在大词汇量语音识别任务中进行了评估
As the use of found data increases, more systems are being built using adaptive training. Here transforms are used to represent unwanted acoustic variability, e.g. speaker and acoustic environment changes, allowing a canonical model that models only the "pure" variability of speech to be trained. Adaptive training may be described within a Bayesian framework. By using complexity control approaches to ensure robust parameter estimates, the standard point estimate adaptive training can be justified within this Bayesian framework. However during recognition there is usually no control over the amount of data available. It is therefore preferable to be able to use a full Bayesian approach to applying transforms during recognition rather than the standard point estimates. This paper discusses various approximations to Bayesian approaches including a new variational Bayes approximation. The application of these approaches to state-of-the-art adaptively trained systems using both CAT and MLLR transforms is then described and evaluated on a large vocabulary speech recognition task