Automatic complexity control for HLDA systems
Automatic complexity control for HLDA systems
复制标题
DOI：
10.1109/icassp.2003.1198734
复制
发表时间：
2003-04
期刊：
影响因子：
--
通讯作者：
Xunying Liu;M. Gales;P. Woodland
中科院分区：
文献类型：
--
作者：
Xunying Liu;M. Gales;P. Woodland
设计一个先进的大词汇量语音识别系统是一个非常复杂的问题。有很多技术可以影响自由参数的性能和数量。选择合适的系统复杂度既费时又只能检查有限数量的可能系统。本文提出了初步的结果，自动系统的选择时，尺寸和组件的数量都不同。各种复杂性控制方案进行了讨论和评估。计划的基础上预测持有的数据对数似然的限制进行了说明。此外，这个任务的标准近似的问题进行了详细说明。
Designing a state-of-the-art large vocabulary speech recognition systems is a highly complex problem. A wide range of techniques are available that affect the performance and number of free parameters. Selecting the appropriate complexity of system is both time-consuming and only a limited number of possible systems can be examined. This paper presents initial results on automatic system selection when both the number of dimensions and the number of components vary. Various complexity control schemes are discussed and evaluated. Limitations of schemes based on predicting held-out data log-likelihoods are described. In addition, problems of standard approximations for this task are detailed.