通过与预先录制的单词进行比较来识别 [英] Recognition by comparison with pre-recorded words

问题描述

要求:

我想要一个与汽车中的呼叫系统类似的系统/算法，您说出您想呼叫的名字，它将找出与您的声音相匹配的名字.我的要求是，我将使用预先录制的声音代替姓名.

I want a system/algorithm that is similar to the call system in the car that you say a name that you want to call, it will find out that name match your voice. My requirement is that I will use pre-recorded voices instead of Name.

例如: 用户使用非英语语言记录几个单词的目标语音，例如:

e.g.: User record target voices for several words in non-English language, e.g.:

• "Keyboard-JP-01.wav" =>键盘
• "Monitor-JP-01.wav" =>显示器

经过一些培训甚至没有进行培训，当用户再次说出一个单词时，语音识别器应该能够识别出它是哪个单词.

After some training or even no training, when the user speak a word again, the speech recognizer should able to identify which word it is.

已知工具:

我搜索了现有的语音识别算法，但找不到一种，其中大多数是在识别现有的语言(从语音到文本的识别).

I searched existing speech recognition algorithm, but cannot find one, most of them are recognizing existing languages (kind of speech to text).

它也不同于语音算法，后者似乎仅适用于英语.

It also different from phonetic algorithm which seems only for English.

谢谢

推荐答案

动态时间扭曲是用于这种语音识别的传统且相当简单的算法，尽管我相信当今必须有更好的方法.

Dynamic Time Warping is a traditional and fairly simple algorithm for this kind of speech recognition, though I'm sure there must be better methods nowadays.

这篇关于通过与预先录制的单词进行比较来识别的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！