Dealing with out-of-vocabulary words and speech disfluencies in an n-gram based speech understanding system
Dealing with out-of-vocabulary words and speech disfluencies in an n-gram based speech understanding system
复制标题
在基于 n-gram 的语音理解系统中处理词汇外的单词和语音不流畅
DOI：
10.21437/icslp.1998-648
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
S. Nakagawa
中科院分区：
文献类型：
--
作者：
A. Kai;Y. Hirose;S. Nakagawa
在本研究中，我们研究了未知文字处理 (UWP) 算法的有效性 (cid:11)，该算法被纳入基于 N-gram 语言模型的语音识别系统中，用于处理 (cid:12) 填充停顿和词汇外 (OOV) 单词。我们已经研究了 UWP 算法的效果，该算法利用简单的子字序列解码器，在使用上下文无关语法 (CFG) 作为语言模型的口语对话系统中。使用基于 N 的连续语音识别系统在小型对话任务和大词汇量阅读语音听写任务上研究了 UWP 算法的效果。实验结果表明，UWP 提高了识别精度，并且与基于 CFG 的系统相比，基于 N-gram 的 UWP 系统可以提高理解性能。
In this study, we investigate the e(cid:11)ectiveness of an unknown word processing(UWP) algorithm, which is incorporated into an N-gram language model based speech recognition system for dealing with (cid:12)lled pauses and out-of-vocabulary(OOV) words. We have already been investigated the e(cid:11)ect of the UWP algorithm, which utilizes a simple subword sequence decoder, in a spoken dialog sys-tem using a context free grammar(CFG) as a language model. The e(cid:11)ect of the UWP algorithm was investigated using an N-based continuous speech recognition system on both a small dialog task and a large-vocabulary read speech dictation task. The experiment results showed that the UWP improves the recognition accuracy and an N-gram based system with the UWP can improve the understanding performance in compared with a CFG-based system.