公开(公告)号：US08874440B2

公开(公告)日：2014-10-28

申请号：US12761489

申请日：2010-04-16

Applicant: Chi-youn Park ,  Nam-hoon Kim ,  Jeong-mi Cho

Inventor： Chi-youn Park ,  Nam-hoon Kim ,  Jeong-mi Cho

IPC: G10L15/00 ,  G10L25/78 ,  G10L25/24 ,  G10L25/09 ,  G10L25/90 ,  G10L25/18

CPC classification number: G10L25/78 ,  G10L25/09 ,  G10L25/18 ,  G10L25/24 ,  G10L25/90

Abstract: A speech detection apparatus and method are provided. The speech detection apparatus and method determine whether a frame is speech or not using feature information extracted from an input signal. The speech detection apparatus may estimate a situation related to an input frame and determine which feature information is required for speech detection for the input frame in the estimated situation. The speech detection apparatus may detect a speech signal using dynamic feature information that may be more suitable to the situation of a particular frame, instead of using the same feature information for each and every frame.

Abstract translation: 提供语音检测装置和方法。 语音检测装置和方法使用从输入信号提取的特征信息来确定帧是否是语音。 语音检测装置可以在估计的情况下估计与输入帧相关的情况并确定哪个特征信息是用于输入帧的语音检测所需要的。 语音检测装置可以使用可能更适合于特定帧的情况的动态特征信息来检测语音信号，而不是为每个帧使用相同的特征信息。

公开(公告)号：US08396708B2

公开(公告)日：2013-03-12

申请号：US12695185

申请日：2010-01-28

Applicant: Chi-youn Park ,  Young-kyoo Hwang ,  Jung-bae Kim

Inventor： Chi-youn Park ,  Young-kyoo Hwang ,  Jung-bae Kim

IPC: G10L15/00 ,  G10L13/00 ,  G10L11/00

CPC classification number: G10L17/26 ,  G06K9/00268 ,  G06K9/00315 ,  G10L2021/105

Abstract: An avatar facial expression representation technology is provided. The avatar facial expression representation technology estimates changes in emotion and emphasis in a user's voice from vocal information, and changes in mouth shape of the user from pronunciation information of the voice. The avatar facial expression technology tracks a user's facial movements and changes in facial expression from image information and may represent avatar facial expressions based on the result of the these operations. Accordingly, the avatar facial expressions can be obtained which are similar to actual facial expressions of the user.

Abstract translation: 提供头像面部表情表示技术。 头像面部表情表示技术根据声音信息估算用户声音中的情感和重点变化，以及用户的声音从语音的发音信息的变化。 头像表情技术从图像信息跟踪用户的面部运动和面部表情的变化，并且可以基于这些操作的结果来表示头像的面部表情。 因此，可以获得类似于用户的实际面部表情的化身面部表情。