An A* algorithm for very large vocabulary continuous speech recognition

HLT '91: Proceedings of the workshop on Speech and Natural Language(1992)

引用 10|浏览0
暂无评分
摘要
We present a new search algorithm for very large vocabulary continuous speech recognition. Continuous speech recognition with this algorithm is only about 10 times more computationally expensive than isolated word recognition. We report preliminary recognition results obtained by testing our recognizer on "books on tape" using a 60,000 word dictionary.
更多
查看译文
关键词
new search algorithm,word dictionary,preliminary recognition result,continuous speech recognition,isolated word recognition,large vocabulary continuous speech,word recognition,search algorithm
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要