386 lines
4.9 KiB
HTML
386 lines
4.9 KiB
HTML
<HTML
|
|
><HEAD
|
|
><TITLE
|
|
>Speech Recognition HOWTO</TITLE
|
|
><META
|
|
NAME="GENERATOR"
|
|
CONTENT="Modular DocBook HTML Stylesheet Version 1.76b+
|
|
"><LINK
|
|
REL="NEXT"
|
|
TITLE="Legal Notices"
|
|
HREF="legal.html"></HEAD
|
|
><BODY
|
|
CLASS="ARTICLE"
|
|
BGCOLOR="#FFFFFF"
|
|
TEXT="#000000"
|
|
LINK="#0000FF"
|
|
VLINK="#840084"
|
|
ALINK="#0000FF"
|
|
><DIV
|
|
CLASS="ARTICLE"
|
|
><DIV
|
|
CLASS="TITLEPAGE"
|
|
><H1
|
|
CLASS="TITLE"
|
|
><A
|
|
NAME="AEN2">Speech Recognition HOWTO</H1
|
|
><H3
|
|
CLASS="AUTHOR"
|
|
><A
|
|
NAME="AEN4"
|
|
>Stephen Cook</A
|
|
></H3
|
|
><DIV
|
|
CLASS="AFFILIATION"
|
|
><DIV
|
|
CLASS="ADDRESS"
|
|
><P
|
|
CLASS="ADDRESS"
|
|
> scook@gear21.com<br>
|
|
</P
|
|
></DIV
|
|
></DIV
|
|
><DIV
|
|
CLASS="REVHISTORY"
|
|
><TABLE
|
|
WIDTH="100%"
|
|
BORDER="0"
|
|
><TR
|
|
><TH
|
|
ALIGN="LEFT"
|
|
VALIGN="TOP"
|
|
COLSPAN="3"
|
|
><B
|
|
>Revision History</B
|
|
></TH
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revision v2.0</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>April 19, 2002</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revised by: scc</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
COLSPAN="3"
|
|
>Changed license information (now GFDL) and added a new publication.</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revision v1.2</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>February 5, 2002</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revised by: scc</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
COLSPAN="3"
|
|
>Added more commercial software listings (sent by Mayur Patel).</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revision v1.1</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>October 5, 2001</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revised by: scc</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
COLSPAN="3"
|
|
>Added info for Vocalis Speechware. Fixed/Updated various other items.</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revision v1.0</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>November 20, 2000</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revised by: scc</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
COLSPAN="3"
|
|
>Added info on L and H and HTK</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revision v0.5</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>September 13, 2000</TD
|
|
><TD
|
|
ALIGN="LEFT"
|
|
>Revised by: scc</TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
ALIGN="LEFT"
|
|
COLSPAN="3"
|
|
>Initial HOWTO Submission</TD
|
|
></TR
|
|
></TABLE
|
|
></DIV
|
|
><DIV
|
|
><DIV
|
|
CLASS="ABSTRACT"
|
|
><A
|
|
NAME="AEN36"><P
|
|
></P
|
|
><P
|
|
>Automatic Speech Recognition (ASR) on Linux is becoming easier.
|
|
Several packages are available for users as well as developers.
|
|
This document describes the basics of speech recognition and
|
|
describes some of the available software.
|
|
</P
|
|
><P
|
|
></P
|
|
></DIV
|
|
></DIV
|
|
><HR></DIV
|
|
><DIV
|
|
CLASS="TOC"
|
|
><DL
|
|
><DT
|
|
><B
|
|
>Table of Contents</B
|
|
></DT
|
|
><DT
|
|
>1. <A
|
|
HREF="legal.html"
|
|
>Legal Notices</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>1.1. <A
|
|
HREF="legal.html#COPYRIGHT"
|
|
>Copyright/License</A
|
|
></DT
|
|
><DT
|
|
>1.2. <A
|
|
HREF="legal.html#DISCLAIMER"
|
|
>Disclaimer</A
|
|
></DT
|
|
><DT
|
|
>1.3. <A
|
|
HREF="legal.html#TRADEMARKS"
|
|
>Trademarks</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
><DT
|
|
>2. <A
|
|
HREF="forward.html"
|
|
>Forward</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>2.1. <A
|
|
HREF="forward.html#ABOUT"
|
|
>About This Document</A
|
|
></DT
|
|
><DT
|
|
>2.2. <A
|
|
HREF="forward.html#ACKNOWLEDGEMENTS"
|
|
>Acknowledgements</A
|
|
></DT
|
|
><DT
|
|
>2.3. <A
|
|
HREF="forward.html#COMMENTS"
|
|
>Comments/Updates/Feedback</A
|
|
></DT
|
|
><DT
|
|
>2.4. <A
|
|
HREF="forward.html#TODO"
|
|
>ToDo</A
|
|
></DT
|
|
><DT
|
|
>2.5. <A
|
|
HREF="forward.html#REVISION"
|
|
>Revision History</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
><DT
|
|
>3. <A
|
|
HREF="introduction.html"
|
|
>Introduction</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>3.1. <A
|
|
HREF="introduction.html#BASICS"
|
|
>Speech Recognition Basics</A
|
|
></DT
|
|
><DT
|
|
>3.2. <A
|
|
HREF="introduction.html#TYPES"
|
|
>Types of Speech Recognition</A
|
|
></DT
|
|
><DT
|
|
>3.3. <A
|
|
HREF="introduction.html#USES"
|
|
>Uses and Applications</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
><DT
|
|
>4. <A
|
|
HREF="hardware.html"
|
|
>Hardware</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>4.1. <A
|
|
HREF="hardware.html#SOUNDCARDS"
|
|
>Sound Cards</A
|
|
></DT
|
|
><DT
|
|
>4.2. <A
|
|
HREF="hardware.html#MICROPHONES"
|
|
>Microphones</A
|
|
></DT
|
|
><DT
|
|
>4.3. <A
|
|
HREF="hardware.html#COMPUTERS"
|
|
>Computers/Processors</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
><DT
|
|
>5. <A
|
|
HREF="software.html"
|
|
>Speech Recognition Software</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>5.1. <A
|
|
HREF="software.html#FREESOFTWARE"
|
|
>Free Software</A
|
|
></DT
|
|
><DT
|
|
>5.2. <A
|
|
HREF="software.html#COMSOFTWARE"
|
|
>Commercial Software</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
><DT
|
|
>6. <A
|
|
HREF="inside.html"
|
|
>Inside Speech Recognition</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>6.1. <A
|
|
HREF="inside.html#RECOGNIZERS"
|
|
>How Recognizers Work</A
|
|
></DT
|
|
><DT
|
|
>6.2. <A
|
|
HREF="inside.html#DIGITALAUDIO"
|
|
>Digital Audio Basics</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
><DT
|
|
>7. <A
|
|
HREF="publications.html"
|
|
>Publications</A
|
|
></DT
|
|
><DD
|
|
><DL
|
|
><DT
|
|
>7.1. <A
|
|
HREF="publications.html#BOOKS"
|
|
>Books</A
|
|
></DT
|
|
><DT
|
|
>7.2. <A
|
|
HREF="publications.html#INTERNET"
|
|
>Internet</A
|
|
></DT
|
|
></DL
|
|
></DD
|
|
></DL
|
|
></DIV
|
|
></DIV
|
|
><DIV
|
|
CLASS="NAVFOOTER"
|
|
><HR
|
|
ALIGN="LEFT"
|
|
WIDTH="100%"><TABLE
|
|
SUMMARY="Footer navigation table"
|
|
WIDTH="100%"
|
|
BORDER="0"
|
|
CELLPADDING="0"
|
|
CELLSPACING="0"
|
|
><TR
|
|
><TD
|
|
WIDTH="33%"
|
|
ALIGN="left"
|
|
VALIGN="top"
|
|
> </TD
|
|
><TD
|
|
WIDTH="34%"
|
|
ALIGN="center"
|
|
VALIGN="top"
|
|
> </TD
|
|
><TD
|
|
WIDTH="33%"
|
|
ALIGN="right"
|
|
VALIGN="top"
|
|
><A
|
|
HREF="legal.html"
|
|
ACCESSKEY="N"
|
|
>Next</A
|
|
></TD
|
|
></TR
|
|
><TR
|
|
><TD
|
|
WIDTH="33%"
|
|
ALIGN="left"
|
|
VALIGN="top"
|
|
> </TD
|
|
><TD
|
|
WIDTH="34%"
|
|
ALIGN="center"
|
|
VALIGN="top"
|
|
> </TD
|
|
><TD
|
|
WIDTH="33%"
|
|
ALIGN="right"
|
|
VALIGN="top"
|
|
>Legal Notices</TD
|
|
></TR
|
|
></TABLE
|
|
></DIV
|
|
></BODY
|
|
></HTML
|
|
> |