I have installed Debian 7.5 in VMplayer, this documents record problem and command needed for this kind of situation. ISO download link. (I choose ‘debian-7.5.0-amd64-netinst.iso’, because this is small and only use one file. While it needs internet to download the other parts of file during the installation. ) 1 Add user to sudoer list: su visudo […]
Centos 6.7，常见问题。 I was installing Centos 6.7 in VMware player, lots of library need to be installed at first. And many problems need to be dealt with. This post documents all the command I have used to deal with different situations 1 Install common library: (http://blog.csdn.net/clevercode/article/details/45438401) yum install -y gcc gdb strace gcc-c++ autoconf libjpeg libjpeg-devel […]
For every person who is interested in speech. The anatomy of human speech system is always leaned through imagination, although you can see lot of descriptions and corresponding pictures. Things still can not be understood intuitively. Here I want to illustrate this idea with more animation to give a more comprehensible description. [ https://zygotebody.com/zb#nav=1.37,87.59,300,0,0,0,0&sel=p:;h:;s:;c:0;o:0&layers=1,1,10000 http://2.bp.blogspot.com/-j3utr1VsiD8/T0ulHEPj6iI/AAAAAAAABe0/hLw_emH-LsY/s1600/112.tif ]
In this post, I want to talk about what kind of knowledge speech can be related to and then make some plan for my future study in speech area. The picture below is a draft for building this post. When the post is finished. Draft will be deleted and replaced with a more clear structure.
”’ This project is from an interview task. It is accomplished in 3 days, which include literature review, corpus prep and model training. Thus many things are not tuning in to the best way. I will update it in the future. Currently, this post will record the thinking and solution to this gender classification task. […]
Click this link to the original paper. Main Point This paper proposed a HMM-free speech recognition system, which consists of an end-to-end model outputting conditional probability of character sequences given acoustic signal and a corresponding decoding mechanism to output the recognition result. The end-to-end model can be divided into two parts, a encoder and a […]