How to detect homophone

♀尐吖头ヾ 提交于 2019-12-13 12:42:38

问题


I am fairly new to speech processing, but wondering how homophones are detected. I am in search for an API which gives similarity between two words on the basis of how they are pronounced.

for example: "to" and "two" are highly similar in terms of how they sound with respect to say "to" and "from".


回答1:


You might want to try calculating the edit distance not on the original strings, but on pronunciations, like they are available in the CMU Pronouncing Dictionary at http://www.speech.cs.cmu.edu/cgi-bin/cmudict




回答2:


The following are used for indexing words by their English pronunciation Soundex or Metaphone. You can use python packages like Fuzzy that implement several indexing algorithms.

import fuzzy


来源:https://stackoverflow.com/questions/26134036/how-to-detect-homophone

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!