arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/0111064cs.CL
收藏

一种无监督的词典学习方法

A procedure for unsupervised lexicon learning

Anand Venkataraman

摘要:

我们描述了一个增量无监督的过程来学习单词从转录的连续语音。该算法是基于一个保守的和传统的统计模型,和实证测试的结果表明,它是有竞争力的其他算法,最近已经提出了这项任务。

英文摘要:

We describe an incremental unsupervised procedure to learn words from transcribed continuous speech. The algorithm is based on a conservative and traditional statistical model, and results of empirical tests show that it is competitive with other algorithms that have been proposed recently for this task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑