公开(公告)号：US20030033144A1

公开(公告)日：2003-02-13

申请号：US10172593

申请日：2002-06-13

Applicant: Apple Computer, Inc.

Inventor： Kim E. Silverman ,  Laurent J. Cerveau ,  Matthias U. Neeracher

IPC: G10L015/00

CPC classification number: G10L15/20 ,  G10L2021/02165 ,  G10L2021/02166

Abstract: A method for speech recognition is provided. Generally, a first signal is generated from a first microphone. The first signal is transformed to coefficients. The coefficients from the first signal are inputted to a multiple channel noise rejection device. A second signal is generated from a second microphone. The second signal is transformed to coefficients. The coefficients from the second signal are inputted to the multiple channel noise rejection device. Coefficients from the multiple channel noise rejection device, which are dependent on coefficients from the first signal and coefficients from the second signal, are provided to an acoustic model selector. Acoustic model hypotheses are chosen based on the coefficients from the multiple channel noise rejection device.

Abstract translation: 提供语音识别的方法。 通常，从第一麦克风产生第一信号。 第一个信号被转换成系数。 来自第一信号的系数被输入到多声道噪声抑制装置。 从第二麦克风产生第二信号。 第二个信号被转换成系数。 来自第二信号的系数被输入到多声道噪声抑制装置。 来自多通道噪声抑制装置的取决于来自第一信号的系数和来自第二信号的系数的系数被提供给声学模型选择器。 基于来自多通道噪声抑制装置的系数来选择声学模型假设。