Bayesian Adaptive Inference and Adaptive Training
Bayesian Adaptive Inference and Adaptive Training
复制标题
DOI：
10.1109/tasl.2007.901300
复制
发表时间：
2007-08
期刊：
影响因子：
--
通讯作者：
Kai Yu;M. Gales
中科院分区：
文献类型：
--
作者：
Kai Yu;M. Gales
大词汇量的语音识别系统通常使用找到的数据构建，例如广播新闻。与仔细收集的数据相比，发现的数据通常包含多种声学条件，例如扬声器或环境噪声。自适应训练是基于此类数据构建系统的强大方法。这里，变换用于表示不同的声学条件，然后在给定这组变换的情况下训练规范模型。本文描述了一个贝叶斯框架的自适应训练和推理。该框架解决了标准最大似然法的一些局限性。与标准方法相比，自适应训练的系统可以直接用于无监督推理，而不必依赖于存在的初始假设。此外，对于有限的自适应数据，可以获得鲁棒的识别性能。有限数据问题经常发生在测试中，因为无法控制可用的自适应数据量。相比之下，对于自适应训练，可以控制系统复杂度以反映可用数据。因此，可以使用标准点估计。由于与贝叶斯自适应推理相关的积分是难以处理的，因此描述了各种边缘化近似，包括变分贝叶斯近似。批量和增量模式的自适应推理进行了讨论。这些方法适用于最大似然线性回归的自适应训练，并在大词汇量语音识别任务上进行评估。贝叶斯自适应推理显着优于标准方法。
Large-vocabulary speech recognition systems are often built using found data, such as broadcast news. In contrast to carefully collected data, found data normally contains multiple acoustic conditions, such as speaker or environmental noise. Adaptive training is a powerful approach to build systems on such data. Here, transforms are used to represent the different acoustic conditions, and then a canonical model is trained given this set of transforms. This paper describes a Bayesian framework for adaptive training and inference. This framework addresses some limitations of standard maximum-likelihood approaches. In contrast to the standard approach, the adaptively trained system can be directly used in unsupervised inference, rather than having to rely on initial hypotheses being present. In addition, for limited adaptation data, robust recognition performance can be obtained. The limited data problem often occurs in testing as there is no control over the amount of the adaptation data available. In contrast, for adaptive training, it is possible to control the system complexity to reflect the available data. Thus, the standard point estimates may be used. As the integral associated with Bayesian adaptive inference is intractable, various marginalization approximations are described, including a variational Bayes approximation. Both batch and incremental modes of adaptive inference are discussed. These approaches are applied to adaptive training of maximum-likelihood linear regression and evaluated on a large-vocabulary speech recognition task. Bayesian adaptive inference is shown to significantly outperform standard approaches.