公开(公告)号：US09843859B2

公开(公告)日：2017-12-12

申请号：US14724375

申请日：2015-05-28

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： Cheah Heng Tan ,  Linus Francis ,  Robert J. Novorita

IPC: G10L21/00 ,  H04R1/46 ,  G10L21/0364 ,  H04R1/10 ,  G10L21/02 ,  G10L19/26 ,  H04R3/00

CPC classification number: H04R1/46 ,  G10L19/265 ,  G10L21/0364 ,  H04R1/1016 ,  H04R3/005 ,  H04R2460/13

Abstract: Preprocessing speech signals from an indirect conduction microphone. One exemplary method preprocesses the speech signal in two stages. In stage one, an external speech sample is characterized using an auto regression model, and coefficients from the model are convolved with the internal speech signal from the indirect conduction microphone to produce a pre-conditioned internal speech signal. In stage two, a training sound is received by the indirect conduction microphone and filtered through a low-pass filter. The result is then modeled using auto regression, and inverted to produce an inverted filter model. The pre-conditioned internal speech signal is convolved with the inverted filter model to remove negative or undesirable acoustic characteristics and loss from the speech signal from the indirect conduction microphone.

公开(公告)号：US20160351203A1

公开(公告)日：2016-12-01

申请号：US14724375

申请日：2015-05-28

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： Cheah Heng Tan ,  Linus Francis ,  Robert J. Novorita

IPC: G10L21/02 ,  H04R1/46

CPC classification number: H04R1/46 ,  G10L19/265 ,  G10L21/0364 ,  H04R1/1016 ,  H04R3/005 ,  H04R2460/13

Abstract: Preprocessing speech signals from an indirect conduction microphone. One exemplary method preprocesses the speech signal in two stages. In stage one, an external speech sample is characterized using an auto regression model, and coefficients from the model are convolved with the internal speech signal from the indirect conduction microphone to produce a pre-conditioned internal speech signal. In stage two, a training sound is received by the indirect conduction microphone and filtered through a low-pass filter. The result is then modeled using auto regression, and inverted to produce an inverted filter model. The pre-conditioned internal speech signal is convolved with the inverted filter model to remove negative or undesirable acoustic characteristics and loss from the speech signal from the indirect conduction microphone.

Abstract translation: 从间接传导麦克风预处理语音信号。 一个示例性方法分两个阶段对语音信号进行预处理。 在第一阶段，使用自回归模型来表征外部语音样本，并且来自该模型的系数与来自间接传导麦克风的内部语音信号进行卷积以产生预处理的内部语音信号。 在第二阶段，间接传导麦克风接收到训练声，并通过低通滤波器进行滤波。 然后使用自动回归模拟结果，并反转以产生反向过滤器模型。 预处理的内部语音信号与反向滤波器模型进行卷积，以消除来自间接传导麦克风的语音信号的负面或不良声学特性和损耗。