公开(公告)号：US20140207447A1

公开(公告)日：2014-07-24

申请号：US14100884

申请日：2013-12-09

Applicant: Huawei Device Co., Ltd.

Inventor： Hongrui JIANG ,  Xiyong WANG ,  Junbin LIANG ,  Weijun ZHENG ,  Junyang ZHOU

IPC: G10L15/20

CPC classification number: G10L15/20 ,  G10L15/08 ,  G10L25/24 ,  G10L25/84

Abstract: Embodiments of the present invention provide a voice identification method, which includes: obtaining voice data; obtaining a confidence value according to the voice data; obtaining a noise scenario according to the voice data; obtaining a confidence threshold corresponding to the noise scenario; and if the confidence value is greater than or equal to the confidence threshold, processing the voice data. An apparatus is also provided. The method and apparatus that flexibly adjust the confidence threshold according to the noise scenario greatly improve a voice identification rate under a noise environment.

Abstract translation: 本发明的实施例提供一种语音识别方法，包括：获取语音数据; 根据语音数据获取置信度值; 根据语音数据获得噪声场景; 获得对应于噪声场景的置信阈值; 并且如果置信度值大于或等于置信度阈值，则处理语音数据。 还提供了一种装置。 根据噪声场景灵活调整置信阈值的方法和装置大大提高了噪声环境下的语音识别率。

公开(公告)号：US20150141079A1

公开(公告)日：2015-05-21

申请号：US14586118

申请日：2014-12-30

Applicant: HUAWEI DEVICE CO., LTD.

Inventor： Xiyong WANG ,  Hongrui JIANG ,  Weijun ZHENG ,  Qing WANG

IPC: H04M1/60 ,  G10L15/00 ,  G10L17/22

CPC classification number: H04M1/6041 ,  G10L15/00 ,  G10L15/26 ,  G10L15/28 ,  G10L17/00 ,  G10L17/22 ,  G10L2015/088 ,  G10L2015/223 ,  H04M1/67 ,  H04M2250/74

Abstract: Embodiments of the present invention disclose a terminal voice control method. The method includes: when a voice instruction of a user is received, identifying the voice instruction, and extracting wake-up indication information from the voice instruction; performing voice verification on the voice instruction if the wake-up indication information is obtained by extracting; and after the voice verification succeeds, extracting processing indication information from the voice instruction, and responding to the voice instruction of the user according to the processing indication information. According to the terminal voice control method in the embodiments of the present invention, a user may use one voice instruction to control a terminal to complete multiple tasks without requiring voice interaction for multiple times, the method is simple to use, and has high security performance.

Abstract translation: 本发明的实施例公开了终端语音控制方法。 该方法包括：当接收到用户的语音指令时，识别语音指令，并从语音指令中提取唤醒指示信息; 如果通过提取获得唤醒指示信息，则对语音指令执行语音验证; 并且在语音验证成功之后，从语音指令提取处理指示信息，并根据处理指示信息响应用户的语音指令。 根据本发明的实施例中的终端语音控制方法，用户可以使用一个语音指令来控制终端完成多个任务而不需要多次语音交互，该方法使用简单，并且具有高安全性能 。

公开(公告)号：US20140207460A1

公开(公告)日：2014-07-24

申请号：US14100822

申请日：2013-12-09

Applicant: Huawei Device Co., Ltd.

Inventor： Hongrui JIANG ,  Xiyong WANG ,  Junbin LIANG ,  Weijun ZHENG ,  Junyang ZHOU

IPC: G10L17/20

CPC classification number: G10L17/20 ,  G10L17/12

Abstract: Embodiments of the present invention provide a voice identification method, including: obtaining voice data; obtaining a first confidence value according to the voice data; obtaining a noise scenario according to the voice data; obtaining a second confidence value corresponding to the noise scenario according to the first confidence value; and if the second confidence value is greater than or equal to a pre-stored confidence threshold, processing the voice data. An apparatus is also provided. The method and apparatus that flexibly adjust the confidence value according to the noise scenario greatly improve a voice identification rate under a noise environment.

Abstract translation: 本发明的实施例提供一种语音识别方法，包括：获取语音数据; 根据语音数据获得第一置信度值; 根据语音数据获得噪声场景; 根据第一置信度获得对应于噪声场景的第二置信度值; 并且如果第二置信度值大于或等于预先存储的置信度阈值，则处理语音数据。 还提供了一种装置。 根据噪声场景灵活调整置信度的方法和装置大大提高了噪声环境下的语音识别率。