会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明申请
    • USER IDENTIFICATION METHOD AND DEVICE
    • 用户识别方法和设备
    • WO2003056521A2
    • 2003-07-10
    • PCT/IB2002/005566
    • 2002-12-17
    • KONINKLIJKE PHILIPS ELECTRONICS N.V.PHILIPS CORPORATE INTELLECTUAL PROPERTY GMBHSTEINBISS, Volker
    • STEINBISS, Volker
    • G07C9/00
    • G06K9/00G06F21/32G06K9/00892G07C9/00158G10L17/10
    • A user identification method is described in which, in a first identification procedure, identification data (ID1) of a first type belonging to a target individual to be identified are determined and are compared with previously stored user identification data (ND1) of the first type assigned to an authorized user. In addition, identification data (ID2) of a second type that belong with a certain probability to the same target individual are automatically determined. After a successful confirmation of the identify of the target individual with the authorized user from the identification data (ID1) of the first type, user identification data (ND2) of the second type are stored for the respective authorized user using the determined identification data (ID2) of the second type in order to use said data in a subsequent identification procedure. In addition, a corresponding user identification device is disclosed.
    • 描述了一种用户识别方法,其中在第一识别过程中,确定属于要识别的目标个体的第一类型的识别数据(ID1),并与先前存储的第一类型的用户识别数据(ND1)进行比较 分配给授权用户。 此外,自动确定属于同一目标个体的一定概率的第二类型的识别数据(ID2)。 在从第一类型的识别数据(ID1)成功地确认了具有授权用户的目标个体的识别之后,使用所确定的标识数据为相应的授权用户存储第二类型的用户识别数据(ND2) ID2),以便在随后的识别过程中使用所述数据。 此外,公开了相应的用户识别装置。
    • 4. 发明申请
    • METHOD OF OPERATING A SPEECH RECOGNITION SYSTEM
    • 操作语音识别系统的方法
    • WO2003054854A2
    • 2003-07-03
    • PCT/IB2002/005471
    • 2002-12-16
    • KONINKLIJKE PHILIPS ELECTRONICS N.V.PHILIPS CORPORATE INTELLECTUAL PROPERTY GMBHSTEINBISS, Volker
    • STEINBISS, Volker
    • G10L15/00
    • G10L15/28G06F21/32G10L2015/228
    • A description is given of methods of operating a speech recognition system (1, 10) in which methods a speech signal from a user is analyzed for recognizing speech information contained in the speech signal. In a first method the speech recognition system (1), when situated in an active receive mode, produces an acknowledgement of receive activity (B) in response to an enquiry about receive activity (A) from a user. In a second method, before speech data (S) comprising at least a portion of the speech signal and/or at least a portion of the speech information are transmitted from an internal user-controlled area (I) into an external area (E), the respective speech data (S) are filtered and/or a message is sent to the user that a transmission of speech data (S) to the external area (E) is imminent. In addition, associated speech recognition systems (1, 10) are described.
    • 给出了操作语音识别系统(1,10)的方法的描述,其中分析来自用户的语音信号的方法以识别语音信号中包含的语音信息。 在第一种方法中,语音识别系统(1)当处于主动接收模式时,响应于关于来自用户的接收活动(A)的询问,产生接收活动的确认(B)。 在第二种方法中,在将包含语音信号的至少一部分的语音数据(S)和/或语音信息的至少一部分从内部用户控制区域(I)发送到外部区域(E)之前, ,对各个语音数据(S)进行滤波和/或向用户发送向外部区域(E)发送语音数据(S)的消息。 另外,描述了相关联的语音识别系统(1,10)。
    • 5. 发明申请
    • MLSE EQUALIZER FOR CORRELATED INTERFERENCE SIGNALS
    • MLSE均衡器用于相关干扰信号
    • WO2003047193A1
    • 2003-06-05
    • PCT/IB2002/004935
    • 2002-11-26
    • KONINKLIJKE PHILIPS ELECTRONICS N.V.PHILIPS CORPORATE INTELLECTUAL PROPERTY GMBHPETERSEN, JuergenWAGNER, Thomas
    • PETERSEN, JuergenWAGNER, Thomas
    • H04L25/03
    • H04L25/0212H04L25/03248
    • An equal performing MLSE (Viterbi algorithm) in the presence of coloured noise is proposed. For each state (S n ) in the trellis an error sequence (e) is stored. This error sequence is determined from the difference between the received and the estimated signal sequence. For each state, the error sequence is fed into a corresponding noise-prediction filter, the output of which is subtracted from the received sequence. The overall branch metric (λ) thus is calculated from the difference of the sum of the estimated signal plus predicted noise and the received signal (r n ). The coefficients (p i ) of the noise-prediction filter are obtained from the auto-correlation function of the noise which might be estimated within the training sequence. A simplified version is also proposed, i. E. to use only one noise-prediction filter for all states.
    • 提出了在存在彩色噪声的情况下执行相等的MLSE(维特比算法)。 对于网格中的每个状态(Sn),存储错误序列(e)。 该误差序列根据接收到的信号序列与估计的信号序列之间的差异来确定。 对于每个状态,误差序列被馈送到相应的噪声预测滤波器中,其输出从接收到的序列中减去。 因此,根据估计信号加预测噪声和接收信号(rn)的和的差计算总分支量度(lambd)。 噪声预测滤波器的系数(pi)从可能在训练序列中估计的噪声的自相关函数获得。 也提出了一个简化版本, E.对所有状态只使用一个噪声预测滤波器。