arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04744cs.CL
收藏

不用语音词典学汉语发音

Learning to Pronounce Chinese Without a Pronunciation Dictionary

DiDi Labs(滴滴实验室);Admiralty Way(4640 Admiralty Way);Marina del Rey, CA 90292

Christopher Chu, Scot Fang, Kevin Knight

摘要:

我们演示了一个程序,学习发音的中文文本在普通话中,没有发音字典。从非平行的汉字流和汉语音节流出发,建立了一个多对多的字音映射。使用无监督的方法,该程序可以有效地将文字破译为语音。它的标记级字符到音节的准确率为89%,大大超过了先前工作的22%的准确率。

英文摘要:

We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between characters and pronunciations. Using unsupervised methods, the program effectively deciphers writing into speech. Its token-level character-to-syllable accuracy is 89%, which significantly exceeds the 22% accuracy of prior work.

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。

↑