专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09240184B1 Frame-level combination of deep neural network and gaussian mixture models 有权
标题翻译：深层神经网络和高斯混合模型的帧级组合
公开(公告)号：US09240184B1
公开(公告)日：2016-01-19
申请号：US13765002
申请日：2013-02-12
申请人： Hui Lin , Xin Lei , Vincent Vanhoucke
发明人： Hui Lin , Xin Lei , Vincent Vanhoucke
IPC分类号： G10L15/22
CPC分类号： G10L15/22 , G10L15/142
摘要： A method and system for frame-level merging of HMM state predictions determined by different techniques is disclosed. An audio input signal may be transformed into a first and second sequence of feature vector, the sequences corresponding to each other and to a temporal sequence of frames of the audio input signal on a frame-by-frame basis. The first sequence may be processed by a neural network (NN) to determine NN-based state predictions, and the second sequence may be processed by a Gaussian mixture model (GMM) to determine GMM-based state predictions. The NN-based and GMM-based state predictions may be merged as weighted sums for each of a plurality of HMM state on a frame-by-frame basis to determine merged state predictions. The merged state predictions may then be applied to the HMMs to speech content of the audio input signal.
摘要翻译：公开了通过不同技术确定的HMM状态预测的帧级合并的方法和系统。音频输入信号可以被变换为第一和第二特征向量序列，这些序列彼此对应，并且逐帧地基于音频输入信号的帧的时间序列。第一序列可以由神经网络（NN）处理以确定基于NN的状态预测，并且第二序列可以由高斯混合模型（GMM）来处理，以确定基于GMM的状态预测。基于NN和GMM的状态预测可以逐帧合并为多个HMM状态中的每一个的加权和，以确定合并的状态预测。然后可以将合并状态预测应用于HMM到音频输入信号的语音内容。

2. 发明授权

US08725498B1 Mobile speech recognition with explicit tone features 有权
标题翻译：具有明确色调特征的移动语音识别
公开(公告)号：US08725498B1
公开(公告)日：2014-05-13
申请号：US13556856
申请日：2012-07-24
申请人： Yun-hsuan Sung , Meihong Wang , Xin Lei
发明人： Yun-hsuan Sung , Meihong Wang , Xin Lei
IPC分类号： G10L15/02
CPC分类号： G10L15/02 , G10L25/48 , G10L25/90
摘要： A computer-implemented method for digital speech processing, including (1) receiving, at a server computer, digital speech data from a computing device, the digital speech data comprising data points sampled at respective time points; (2) computing, by the server computer, a tonal feature of the digital speech data, the tonal feature comprising information encoding fundamental frequencies at the respective time points; (3) computing, by the server computer, a logarithm of the tonal feature at the respective time points; and (4) processing, by the server computer, the logarithm of the tonal feature based on a characterization of the digital speech data at the respective time points.
摘要翻译：一种用于数字语音处理的计算机实现方法，包括（1）在服务器计算机处接收来自计算设备的数字语音数据，所述数字语音数据包括在各个时间点采样的数据点; （2）由服务器计算机计算数字语音数据的音调特征，该音调特征包括在各个时间点编码基本频率的信息; （3）由服务器计算机计算各个时间点的色调特征的对数; 和（4）由服务器计算机根据在各个时间点的数字语音数据的表征来处理音调特征的对数。

3. 发明申请

US20070129943A1 Speech recognition using adaptation and prior knowledge 审中-公开
标题翻译：使用适应和先验知识的语音识别
公开(公告)号：US20070129943A1
公开(公告)日：2007-06-07
申请号：US11295297
申请日：2005-12-06
申请人： Xin Lei , Jonathan Hamaker , Xiaodong He , Patrick Nguyen
发明人： Xin Lei , Jonathan Hamaker , Xiaodong He , Patrick Nguyen
IPC分类号： G10L15/00
CPC分类号： G10L15/065 , G10L15/063
摘要： A speech recognition system includes a feature extraction component that receives a speech signal and extracts feature vectors from the speech signal. Also included, is a decoder having a speech acoustic model, a feature modification component, and a comparison component. The feature modification component changes the feature vectors, using adaptation data and prior data, to more closely match. the speech acoustic model. The comparison component utilizes the modified feature vectors and the speech acoustic model to recognize the speech signal.
摘要翻译：语音识别系统包括接收语音信号并从语音信号中提取特征向量的特征提取组件。还包括具有语音声学模型，特征修改分量和比较分量的解码器。特征修改组件使用自适应数据和先前数据来改变特征向量以更紧密地匹配。语音模型。比较组件利用修改的特征向量和语音模型识别语音信号。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式