1、VAD的总体步骤:https://www.bbsmax.com/A/1O5EOo73z7/
2、基于短时能量和过零率的简单实现(实际上精确度高的VAD会提取4种或更多的特征进行判断,这里只介绍两种特征的基本方法):https://blog.csdn.net/weixin_42788078/article/details/89634363?depth_1-utm_source=distribute.pc_relevant.none-task&utm_source=distribute.pc_relevant.none-task
3、基于神经网络的实现(Alex):https://www.cnblogs.com/Vanessa-Feng/p/7452016.html
4、相关书籍:hand-book-of-speech-enhancement-and-recognition:https://shichaog1.gitbooks.io/hand-book-of-speech-enhancement-and-recognition/content/chapter7.html
5、WebRTC之VAD算法(python包):https://blog.csdn.net/benhuo931115/article/details/54909228