简体繁体 English

哪些库可用于分析音频文件中的语音关键词和/或语音转文本？

[英]What libraries are available for analyzing audio files for spoken keywords and/or speech to text?

原文 2011-02-02 22:39:56 1 2 java/ c++/ language-agnostic/ audio/ analysis

I'm a super-hero in my off-time and I'm trying to build an application that analyzes audio for spoken keywords. 我是业余时间的超级英雄，我正在尝试构建一个用于分析语音关键词的音频的应用程序。 (Think emergency/911 calls) If a keyword is "robbery", and that word is spoken within the audio provided I would like to flag that file and possibly translate it to text. （考虑紧急情况/ 911电话）如果关键字是“ robbery”，并且在音频中说出了这个词，则我想标记该文件并可能将其翻译为文本。

What development libraries or software applications are out there for doing this sort of thing? 有哪些开发库或软件应用程序可以执行此类操作？ C++ or Java libraries are preferred but not required. 首选C ++或Java库，但不是必需的。

2 个解决方案

Wiki page here is a good starting point. Wiki页面这里是一个很好的起点。 Of the ones mentioned there I think CMU Sphinx is the most active one. 在这里提到的那些中，我认为CMU Sphinx是最活跃的。

You could work with Praat http://www.fon.hum.uva.nl/praat/ , it's an excelent program for working with phonetics and it has it's own scripting language. 您可以与Praat一起使用http://www.fon.hum.uva.nl/praat/ ，这是处理语音的出色程序，并且具有自己的脚本语言。 You can also find a lot of scripts in the Praat community. 您还可以在Praat社区中找到很多脚本。 You can also use sendpraat http://www.fon.hum.uva.nl/praat/sendpraat.html to work with the praat functions as a subroutine. 您还可以使用sendpraat http://www.fon.hum.uva.nl/praat/sendpraat.html将praat函数用作子例程。