Tandem Connectionist Feature Extraction for Conversational Speech Recognition
Tandem Connectionist Feature Extraction for Conversational Speech Recognition
复制标题
用于会话语音识别的串联联结特征提取
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
A. Stolcke
中科院分区：
文献类型：
--
作者：
Q. Zhu;Barry Y. Chen;N. Morgan;A. Stolcke
多层感知器（MLP）可以以多种方式用于自动语音识别。在过去几年中，该工具的一个特殊应用是串联方法，如[7]和其他最近的出版物所述。在这里，我们讨论的特点的MLP为基础的功能，用于串联的方法，并得出结论，他们的应用程序的会话语音识别的报告。该论文表明，MLP变换产生具有规则分布的变量，可以通过使用对数来进一步修改这些变量，以使分布更容易通过Gaussian-HMM建模。这些特征的两个或更多个向量可以容易地组合而不增加特征维度。我们还报告识别结果表明，MLP功能可以显着提高识别性能的NIST 2001集线器-5评估集上的Switchboard语料库训练的模型，即使是复杂的系统，包括MMIE培训和其他增强功能。
Multi-Layer Perceptrons (MLPs) can be used in automatic speech recognition in many ways. A particular application of this tool over the last few years has been the Tandem approach, as described in [7] and other more recent publications. Here we discuss the characteristics of the MLP-based features used for the Tandem approach, and conclude with a report on their application to conversational speech recognition. The paper shows that MLP transformations yield variables that have regular distributions, which can be further modified by using logarithm to make the distribution easier to model by a Gaussian-HMM. Two or more vectors of these features can easily be combined without increasing the feature dimension. We also report recognition results that show that MLP features can significantly improve recognition performance for the NIST 2001 Hub-5 evaluation set with models trained on the Switchboard Corpus, even for complex systems incorporating MMIE training and other enhancements.