发明名称 Speech recognition apparatus and method thereof.
摘要 <p>An orthogonalizing time filter section (11) is arranged in place of a Gram Schmidt orthogonalizing section (8). The orthogonalizing time filter section (11) is constituted by a plurality of filters for performing smoothing processing and differential processing. The orthogonalizing time filter section (11) obtains an average pattern of acquired learning patterns, and smoothes the average pattern along the time base to obtain a dictionary of a first axis. The section (11) differentiates the average pattern along the time base to obtain a dictionary of a second axis. The above processing is repeated for each category, thus generating an orthogonalized dictionary.</p>
申请公布号 EP0311022(B1) 申请公布日期 1994.03.30
申请号 EP19880116414 申请日期 1988.10.04
申请人 KABUSHIKI KAISHA TOSHIBA 发明人 NITTA, TSUNEO
分类号 G10L15/00;(IPC1-7):G10L5/06 主分类号 G10L15/00
代理机构 代理人
主权项
地址