Speech feature extraction apparatus and speech feature extraction method

    公开(公告)号:US09754603B2

    公开(公告)日:2017-09-05

    申请号:US13728287

    申请日:2012-12-27

    IPC分类号: G10L21/00 G10L15/02 G10L15/20

    CPC分类号: G10L21/00 G10L15/02 G10L15/20

    摘要: According to one embodiment, a speech feature extraction apparatus includes an extraction unit and a calculation unit. The extraction unit extracts speech segments over a predetermined period at intervals of a unit time from either an input speech signal or a plurality of subband input speech signals obtained by extracting signal components of a plurality of frequency bands from the input speech signal, to generate either a unit speech signal or a plurality of subband unit speech signals. The calculation unit calculates either each average time of the unit speech signal in each of the plurality of frequency bands or each average time of each of the plurality of subband unit speech signals to obtain a speech feature.

    Speech Feature Extraction Apparatus and Speech Feature Extraction Method
    2.
    发明申请
    Speech Feature Extraction Apparatus and Speech Feature Extraction Method 有权
    语音特征提取装置及语音特征提取方法

    公开(公告)号:US20130179158A1

    公开(公告)日:2013-07-11

    申请号:US13728287

    申请日:2012-12-27

    IPC分类号: G10L21/00

    CPC分类号: G10L21/00 G10L15/02 G10L15/20

    摘要: According to one embodiment, a speech feature extraction apparatus includes an extraction unit and a calculation unit. The extraction unit extracts speech segments over a predetermined period at intervals of a unit time from either an input speech signal or a plurality of subband input speech signals obtained by extracting signal components of a plurality of frequency bands from the input speech signal, to generate either a unit speech signal or a plurality of subband unit speech signals. The calculation unit calculates either each average time of the unit speech signal in each of the plurality of frequency bands or each average time of each of the plurality of subband unit speech signals to obtain a speech feature.

    摘要翻译: 根据一个实施例,语音特征提取装置包括提取单元和计算单元。 提取单元从输入语音信号或通过从输入语音信号提取多个频带的信号分量而获得的多个子带输入语音信号,以单位时间间隔在预定时段内提取语音片段,以产生 单位语音信号或多个子带单元语音信号。 计算单元计算多个频带中的每一个中的单位语音信号的每个平均时间或者多个子带单元语音信号中的每一个的每个平均时间,以获得语音特征。

    Thermostat for two-system cooling device
    8.
    发明申请
    Thermostat for two-system cooling device 失效
    双系统冷却装置恒温器

    公开(公告)号:US20050001044A1

    公开(公告)日:2005-01-06

    申请号:US10494047

    申请日:2003-06-18

    摘要: A thermostat independently controlling cooling water passages of two circuits, including a first valve body having first and second passages in constant communication. A third passage is selectively connected to those passages. Communication of the third passage is disconnected when the cooling water temperature is below a prescribed temperature, and the valve is opened when the cooling water temperature is equal to or higher than the prescribed temperature. A second valve body, having fourth and fifth passages selectively in communication, closes the valve to disconnect those passages when the cooling water temperature is below the prescribed temperature, and opens the valve by operating the first valve body to link the passages when the cooling water temperature is equal to or higher than the prescribed temperature. A tubular sleeve prevents first and second control chambers, respectively including the first and second valve bodies, from communicating with each other.

    摘要翻译: 一种独立控制两个电路的冷却水通道的恒温器,包括具有恒定连通的第一和第二通道的第一阀体。 选择性地连接到第三通道。 当冷却水温度低于规定温度时,第三通道的通信断开,当冷却水温度等于或高于规定温度时,阀门打开。 具有选择性连通的第四和第五通道的第二阀体在冷却水温度低于规定温度时关闭阀门以断开这些通道,并且当冷却水通过操作第一阀体连接通道而打开阀门 温度等于或高于规定温度。 管状套筒防止分别包括第一和第二阀体的第一和第二控制室彼此连通。