如何对android中的本地数据库进行语音识别检查? [英] How to make voice recognition check against a local database in android?

问题描述

你还记得在旧手机中你可以做一个语音快捷方式来打电话给一个人.

Do you remember in old cellphones you could make a speech shortcut to call a person.

我正在尝试使用该功能在 android 中制作一个应用程序.用户录制一个它想要控制应用程序的单词或声音，语音识别器只会检查它听到的声音是否与之前录制的声音相同.

I am trying to make an app in android with that function. The user records a word or sound it wants to control the application with and the voice-recognizer will only check if the sound it hears equals the sound previously recorded.

有人知道如何制作或知道指南吗?我已经找了几个月没有找到满意的解决方案.

Does anyone know how to make this or know of a guide? I've been searching for months without finding a satisfying solution.

谢谢

推荐答案

您需要将参考声音和录制的声音都转换为特征.为此，您需要在帧上分割声音并提取 FFT 或直接提取倒谱.为此，您可以使用任何 MFCC 库.

You need to convert both reference sounds and recorded sound to features. For that you need to split sound on frames and extract FFT or directly mel-cepstrum. You can use any MFCC library out there for that.

得到特征后，可以用DTW算法进行对比.你可以在这里找到一些细节

After you get features, you can compare them with DTW algorithm. You can find some details here

http://en.wikipedia.org/wiki/Dynamic_time_warping

DTW 将返回阈值，您可以使用该阈值来选择合适的呼叫对象.

The DTW will return you the threshold which you can use to select the right person to call to.

类似的问题

测量两个短的相似度的最简单算法音频

这篇关于如何对android中的本地数据库进行语音识别检查?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！