Recognition performance of a structured language model
Recognition performance of a structured language model
复制标题
结构化语言模型的识别性能
DOI：
--
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
F. Jelinek
中科院分区：
文献类型：
--
作者：
Ciprian Chelba;F. Jelinek
受语言分析启发，提出了一种新的语音识别语言模型。该模型逐步开发隐藏的层次结构，并使用它从单词历史中提取有意义的信息，从而能够使用扩展的距离依赖关系，试图补充当前使用的三元组模型的局部性。介绍了结构化语言模型、其概率参数化以及两遍语音识别器中的性能。 SWITCHBOARD 语料库上的实验表明，与传统三元组模型相比，困惑度和错误率都有所改善。
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history — thus enabling the use of extended distance dependencies — in an attempt to complement the locality of currently used trigram models. The structured language model, its probabilistic parameterization and performance in a two-pass speech recognizer are presented. Experiments on the SWITCHBOARD corpus show an improvement in both perplexity and word error rate over conventional trigram models.