Adaptive training for robust ASR
Adaptive training for robust ASR
复制标题
DOI：
10.1109/asru.2001.1034578
复制
发表时间：
2001-09
期刊：
影响因子：
--
通讯作者：
M. Gales
中科院分区：
文献类型：
--
作者：
M. Gales
自适应训练是一种强大的训练技术，用于在非同质数据上构建语音识别系统。目的是从所需的变化（单词之间的声学差异）中消除不需要的变化，例如说话者、通道或声学环境的变化。在训练期间，生成两组模型：用于语音数据所需“真实”变异性的规范模型集，以及用于表示不需要的变异性的一组变换。以这种方式训练的规范模型集应该更“适合”适应特定的目标条件并且更“紧凑”。在识别过程中，训练到目标域的变换。然后，在识别过程中将该目标特定变换与规范模型集一起使用。本文概述了自适应训练中使用的基本理论和假设。此外，还描述了自适应训练方案在当前最先进的任务中的使用，并讨论了未来如何使用此类方案。
Adaptive training is a powerful training technique for building speech recognition systems on nonhomogeneous data. The aim is to remove unwanted variability, such as changes in speaker, channel or acoustic environment, from desired changes, the acoustic differences between words. During training, two sets of models are generated: a canonical model set for the desired "true" variability of the speech data, and a set of transforms to represent the unwanted variability. The canonical model set trained in this fashion should be more "amenable" to being adapted to a particular target condition and more "compact". During recognition, a transform to the target domain is trained. This target specific transform is then used with the canonical model set in the recognition process. The paper gives an overview of the underlying theory and assumptions used in adaptive training. Furthermore, the use of adaptive training schemes in current state-of-the-art tasks is described, together with a discussion of how such schemes may be used in the future.