公开(公告)号：WO2007017853A1

公开(公告)日：2007-02-15

申请号：PCT/IL2005/000848

申请日：2005-08-08

Applicant: NICE SYSTEMS LTD. ,  PEREG, Oren ,  WASERBLAT, Moshe

Inventor： PEREG, Oren ,  WASERBLAT, Moshe

IPC: G10L15/00 ,  G06F17/16

CPC classification number: G10L17/26 ,  G10L15/02

Abstract: An apparatus and method for detecting an emotional state (230) of a speaker participating in an audio signal (204). The apparatus and method are based on the distance in voice features between a person being in an emotional state (218) and the same person being in a neutral state (220). The apparatus and method comprise a training phase in which a training feature vector (224) is determined, and an ongoing stage in which the training feature vector is used to determine emotional states in a working environment. Multiple types of emotions can be detected, and the method and apparatus are speaker-independent, i.e., no prior voice sample or information about the speaker is required.

Abstract translation: 一种用于检测参与音频信号（204）的说话者的情感状态（230）的装置和方法。 该装置和方法基于处于情绪状态的人（218）和处于中立状态（220）的同一人之间的语音特征中的距离。 所述装置和方法包括其中确定训练特征向量（224）的训练阶段，以及训练特征向量用于确定工作环境中的情绪状态的进行阶段。 可以检测多种类型的情绪，并且该方法和装置与扬声器无关，即不需要先前的语音样本或关于说话者的信息。

公开(公告)号：WO2006126183A2

公开(公告)日：2006-11-30

申请号：PCT/IL2006000110

申请日：2006-01-26

Applicant: NICE SYSTEMS LTD ,  WASERBLAT MOSHE ,  EILAM BARAK ,  PEREG OREN ,  KOR ILAN

Inventor： WASERBLAT MOSHE ,  EILAM BARAK ,  PEREG OREN ,  KOR ILAN

IPC: H04M15/00

CPC classification number: H04M3/36 ,  G06Q20/4016 ,  G10L17/26 ,  H04M3/385 ,  H04M2201/41 ,  H04M2203/6027

Abstract: An apparatus and method for detecting a fraud or fraud attempt in a captured interaction. The method comprising a selection step in which interactions suspected as capturing fraud attempts are selected for further analysis, and assigned a first fraud probability, and a fraud detection step in which the voice is scored against one or more voice prints, of the same alleged customer or of known fraudsters. The first fraud or fraud attempt probability is combined with the result of the scoring of the fraud detection step, to generate a total fraud or fraud attempt probability. If the total fraud or fraud attempt probability exceeds a threshold, a notification is issued. The selection, scoring and combination thereof are performed using user-defined rules and thresholds.

Abstract translation: 一种用于检测捕获的交互中的欺诈或欺诈尝试的装置和方法。 所述方法包括选择步骤，其中选择被怀疑为捕获欺诈尝试的交互用于进一步分析，并且分配了第一欺诈概率，以及欺诈检测步骤，其中所述语音针对相同的所述客户的一个或多个语音打印 或已知的欺诈者。 将第一个欺诈或欺诈尝试概率与欺诈检测步骤的评分结果相结合，以产生总的欺诈或欺诈尝试概率。 如果总欺诈或欺诈尝试概率超过阈值，则发出通知。 使用用户定义的规则和阈值来进行选择，评分和组合。