公开(公告)号：WO2012025579A1

公开(公告)日：2012-03-01

申请号：PCT/EP2011/064588

申请日：2011-08-24

Applicant: VEOVOX SA ,  DINES, John ,  CARMONA, Jorge ,  MASSON, Olivier ,  ARADILLA, Guillermo

Inventor： DINES, John ,  CARMONA, Jorge ,  MASSON, Olivier ,  ARADILLA, Guillermo

IPC: G10L15/02 ,  G10L15/06 ,  G10L15/16

CPC classification number: G10L15/02 ,  G10L15/063 ,  G10L15/12 ,  G10L15/16 ,  G10L15/20

Abstract: An automatic speech recognition system for recognizing a user (2) voice command in noisy environment, comprising -matching means for matching elements retrieved from speech units forming said command with templates in a template library (44); characterized by -processing means (32, 36, 38) including a MultiLayer Perceptron (38) for computing posterior templates (P(O template(q) )) stored as said templates in said template library (44); -means for retrieving posterior vectors (P(O test(q) )) from said speech units, said posterior vectors being used as said elements. The present invention relates also to a method for recognizing a user voice command in noisy environments.

Abstract translation: 一种用于在嘈杂环境中识别用户（2）语音命令的自动语音识别系统，包括 - 匹配装置，用于将从形成所述命令的语音单元检索的元素与模板库（44）中的模板相匹配; 其特征在于包括用于计算在所述模板库（44）中作为所述模板存储的后验模板（P（O模板（q）））的多层感知器（38）的处理装置（32,36,38）。 - 用于从所述语音单元检索后向量向量（P（Otest（q））），所述后向量被用作所述元素。 本发明还涉及一种用于在嘈杂环境中识别用户语音命令的方法。

公开(公告)号：WO2011067292A1

公开(公告)日：2011-06-09

申请号：PCT/EP2010/068649

申请日：2010-12-01

Applicant: VEOVOX SA ,  LISSEK, Hervé ,  MARTIN, Philippe ,  CARMONA, Jorge ,  IMHASLY, Michel ,  MILLAR, Ian ,  FALOURD, Xavier ,  MARMAROLI, Patrick ,  MAÎTRE, Gilbert

Inventor： LISSEK, Hervé ,  MARTIN, Philippe ,  CARMONA, Jorge ,  IMHASLY, Michel ,  MILLAR, Ian ,  FALOURD, Xavier ,  MARMAROLI, Patrick ,  MAÎTRE, Gilbert

IPC: H04R1/40 ,  H04M1/60

CPC classification number: H04R1/406 ,  H04M1/035 ,  H04M1/6008 ,  H04R3/005 ,  H04R2410/05

Abstract: A portable voice capture device comprising: an orientable arm with a first differential array of microphones comprising at least one pair of microphones, the directivity of said first array being arranged for sensing voice from a first direction depending on the orientation of said arm; a second differential array of microphones comprising at least one pair of microphones, the directivity of said second array being arranged for sensing noise from a second direction different from the first direction; a noise reduction circuit for providing a voice signal with reduced noise, based on the output of said first array and on the output of said second array.

Abstract translation: 一种便携式语音捕获装置，包括：可定向臂，具有包括至少一对麦克风的麦克风的第一差分阵列，所述第一阵列的方向性被布置用于根据所述臂的取向从第一方向感测声音; 麦克风的第二差分阵列，包括至少一对麦克风，所述第二阵列的方向性布置成用于从不同于第一方向的第二方向感测噪声; 降噪电路，用于基于所述第一阵列的输出和所述第二阵列的输出，提供具有降低的噪声的语音信号。