语音识别学习记录-第一周

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

2013.10.191.Machine learning 公开课第一集(共20 集) 机器学习的动机与应用 2.Paper –[A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition]部分

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

Machine learning 公开课 The classes are provided by Stanford University. I download it from the NetEase Opencourse. The class provides a broad introduction to machine learning and statistical pattern recognition. The topics of the classes are as following: supervised learning unsupervised learning learning theory reinforcement learning adaptive control

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

Machine learning 公开课 The recent applications of machine learning are as following: robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, text and web data processing The pre-requisites of this class: Basic knowledge of computer science; Familiarity with the basic probability theory; Familiarity with the basic linear algebra;

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

Machine learning 公开课 Tow definitions of machine learning Arthur Samuel (1959):Field of study that gives computers the ability to learn without being explicitly programmed. Tom Mitchell (1998) Well-posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performance measured by P, improves with E.

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

Machine learning 公开课 contentSupervised learning Learning theory

Applications and my understanding我的理解：给定意义的数据，找对应关系。 应用：自动驾驶的汽车(需要人先开一段路，是机器完 成学习);机器自己下棋，然后通过输赢，学习怎么下 棋赢得几率大，最终效果可以比实验者下的好。 我的理解：没有解释的数据，发掘数据含义。 应用：2维图片，变为3维浏览方式；多人交流情况下， 分别提取出每个人的声音 (通过两个不同位置的 Microphone)(matlab 实现起来很简单);

Unsupervised learning

Reinforce learning

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition部分

Introduction Section2: discrete Markov processes Section3:three fundamental problems of HMMs Section4:virious types of HMMs Section5:the issues that arise in implementing HMMs Section6:isolated word speech recognition Section7:recognizing a string of spoken words Section8:summarize the ideas

本人从2013年10月开始接触、学习语音识别,speaker verification, speech recognition等。现将每周学习进度制作为PPT,望与大家交流~

A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition部分