Joint uncertainty decoding for noise robust speech recognition
Joint uncertainty decoding for noise robust speech recognition
复制标题
DOI：
10.21437/interspeech.2005-265
复制
发表时间：
2005-09
期刊：
影响因子：
4.9
通讯作者：
H. Liao;M. Gales
中科院分区：
文献类型：
--
作者：
H. Liao;M. Gales
背景噪声会对语音识别系统的性能产生重大影响。为了提高鲁棒性，我们研究了一系列快速特征空间和基于模型的方案。与基于特征的方法相比，基于模型的方法通常可以实现较低的错误率，但计算负载增加。这使得它们在许多情况下的使用不切实际。不确定性解码框架可以被认为是两者之间的优雅折衷。在这里，特征的不确定性以数学上一致的方式传播到识别器。用于确定不确定性的模型的复杂性可以与识别模型本身解耦，从而允许计算负载的灵活性。本文描述了该框架内的一种新方法：联合不确定性解码。该方法与不确定性解码版本的 SPLICE、标准 SPLICE 以及新形式的前端 CMLLR 进行了比较。这些是在带有人工添加噪声的中等词汇量语音识别任务上进行评估的。
Background noise can have a significant impact on the performance of speech recognition systems. A range of fast featurespace and model-based schemes have been investigated to increase robustness. Model-based approaches typically achieve lower error rates, but at an increased computational load compared to feature-based approaches. This makes their use in many situations impractical. The uncertainty decoding framework can be considered an elegant compromise between the two. Here, the uncertainty of features is propagated to the recogniser in a mathematically consistent fashion. The complexity of the model used to determine the uncertainty may be decoupled from the recognition model itself, allowing flexibility in the computational load. This paper describes a new approach within this framework, Joint uncertainty decoding. This approach is compared with the uncertainty decoding version ofSPLICE, standardSPLICE, and a new form of front-end CMLLR. These are evaluated on a medium vocabulary speech recognition task with artificially added noise.