SHORTLIST - A CONNECTIONIST MODEL OF CONTINUOUS SPEECH RECOGNITION
SHORTLIST - A CONNECTIONIST MODEL OF CONTINUOUS SPEECH RECOGNITION
复制标题
DOI：
10.1016/0010-0277(94)90043-4
复制
发表时间：
1994-09-01
期刊：
影响因子：
3.4
通讯作者：
NORRIS, D
中科院分区：
文献类型：
--
作者：
NORRIS, D
先前的工作已经展示了具有循环连接的反向传播网络如何成功地模拟人类口语单词识别的许多方面（Norris，1988，1990，1992，1993）。然而.这些网络无法根据后来的情况修改其决定。TRACE（McClelland & Elman，1986），另一方面，设法适当地处理以下上下文，但只有通过使用一个高度难以置信的架构，未能解释一些重要的实验结果。提出了一种新的模型，它显示了这些模型中的每一个更理想的属性。与TRACE相比，新模型完全是自下而上的，可以很容易地对数万个单词的词汇表进行模拟。
Previous work has shown how a back-propagation network with recurrent connections can successfully model many aspects of human spoken word recognition (Norris, 1988, 1990, 1992, 1993). However. such networks are unable to revise their decisions in the light of subsequent context. TRACE (McClelland & Elman, 1986), on the other hand, manages to deal appropriately with following context, but only by using a highly implausible architecture that fails to account for some important experimental results. A new model is presented which displays the more desirable properties of each of these models. In contrast to TRACE the new model is entirely bottom-up and can readily perform simulations with vocabularies of tens of thousands of words.