Patent for improved discriminative training of a speech recognition system</tile> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> <meta http-equiv="description" content="Patent for improved discriminative training of a speech recognition system"> <meta http-equiv="keywords" content="Patent,for,improved,discriminative,training,of,a,speech,recognition,system"> </head> <body> <table width="100%" border="0" cellspacing="0" cellpadding="0"> <tr> <td width="10" height="39"> </td> <td width="99%" height="39"> <table width="100%" border="0" cellspacing="0" cellpadding="0"> <tr> <td width="16%"><a href="http://inttranews.inttra.net"><img src="http://inttranews.inttra.net/images/inttranews_grey_2.jpg" width="192" height="37" border="0"></a></td> <td width="50%" valign="middle"> <p><font face="Arial, Helvetica, sans-serif" size="2"><b><font color="#CCCCCC" face="Verdana, Arial, Helvetica, sans-serif" size="1">KNOW.<br> HOW.</font></b></font> </p> </td> <td width="34%" align="right" valign="top"><font face="Verdana, Arial, Helvetica, sans-serif" size="1" color="#666666">10-07-2007</font></td> </tr> </table> </td> </tr> <tr> <td width="10"> </td> <td width="99%" > </td> </tr> <tr> <td width="10"> </td> <td width="99%" > <table width="100%" border="0" cellspacing="0" cellpadding="0"> <tr> <td width="100%"><font face="Verdana, Arial, Helvetica, sans-serif" size="2"> <b>Patent for improved discriminative training of a speech recognition system</b></font> </td> </tr> <tr> <td width="100%"> </td> </tr> <tr> <td width="100%"> <img src="http://inttranews.inttra.net/img_news/img_aCwpWnXfltVrw0MuICbz_0.jpg" align="left" vspace="5" hspace="5" ><font face="Verdana, Arial, Helvetica, sans-serif" size="2">Pennsylvania, USA (Post): SpeechWorks International Inc., for "Method and apparatus for discriminative training of acoustic models of a speech recognition system, No. 7,216,079." Inventors were Etienne Barnard, Pittsburgh, and Jean-Guy Dahan, Brookline, Mass. The present invention relates generally to improving performance of automatic speech recognition systems, and relates more specifically to an improved discriminative training approach for acoustic models of a speech recognition system. <br> <br>For more information, please visit: <br><a href="http://www.post-gazette.com/pg/07188/799807-28.stm " target="blank">www.post-gazette.com/pg/07188/799807-28.stm </a> <br></font></td> </tr> </table> </td></tr> </table> <script type="text/javascript"></script> <script type="text/javascript" src="<http://pagead2.googlesyndication.com/pagead/show