公开(公告)号：US08386257B2

公开(公告)日：2013-02-26

申请号：US12439051

申请日：2007-09-13

申请人： Go Irie ,  Kota Hidaka ,  Takashi Satou ,  Yukinobu Taniguchi ,  Shinya Nakajima

发明人： Go Irie ,  Kota Hidaka ,  Takashi Satou ,  Yukinobu Taniguchi ,  Shinya Nakajima

IPC分类号： G10L21/00 ,  G10L15/28 ,  G10L15/18

CPC分类号： G10L17/26

摘要： An audio feature is extracted from audio signal data for each analysis frame and stored in a storage part. Then, the audio feature is read from the storage part, and an emotional state probability of the audio feature corresponding to an emotional state is calculated using one or more statistical models constructed based on previously input learning audio signal data. Then, based on the calculated emotional state probability, the emotional state of a section including the analysis frame is determined.

摘要翻译： 从每个分析帧的音频信号数据中提取音频特征并存储在存储部分中。 然后，从存储部分读取音频特征，并且使用基于先前输入的学习音频信号数据构建的一个或多个统计模型来计算与情绪状态相对应的音频特征的情绪状态概率。 然后，根据计算出的情绪状态概率，确定包含分析框架的部分的情绪状态。

公开(公告)号：US20090265170A1

公开(公告)日：2009-10-22

申请号：US12439051

申请日：2007-09-13

申请人： Go Irie ,  Kouta Hidaka ,  Takashi Satou ,  Yukinobu Taniguchi ,  Shinya Nakajima

发明人： Go Irie ,  Kouta Hidaka ,  Takashi Satou ,  Yukinobu Taniguchi ,  Shinya Nakajima

IPC分类号： G10L15/02

CPC分类号： G10L17/26

摘要： An audio feature is extracted from audio signal data for each analysis frame and stored in a storage part. Then, the audio feature is read from the storage part, and an emotional state probability of the audio feature corresponding to an emotional state is calculated using one or more statistical models constructed based on previously input learning audio signal data. Then, based on the calculated emotional state probability, the emotional state of a section including the analysis frame is determined.

摘要翻译： 从每个分析帧的音频信号数据中提取音频特征并存储在存储部分中。 然后，从存储部分读取音频特征，并且使用基于先前输入的学习音频信号数据构建的一个或多个统计模型来计算与情绪状态相对应的音频特征的情绪状态概率。 然后，根据计算出的情绪状态概率，确定包含分析框架的部分的情绪状态。