发明申请
US20160005399A1 NOISE SPEED-UPS IN HIDDEN MARKOV MODELS WITH APPLICATIONS TO SPEECH RECOGNITION
审中-公开
基本信息:
- 专利标题： NOISE SPEED-UPS IN HIDDEN MARKOV MODELS WITH APPLICATIONS TO SPEECH RECOGNITION
- 专利标题（中）：噪音速度型UPS用于语音识别应用
- 申请号：US14802760 申请日：2015-07-17
- 公开(公告)号：US20160005399A1 公开(公告)日：2016-01-07
- 发明人： Kartik Audhkhasi , Osonde Osoba , Bart Kosko
- 申请人： Kartik Audhkhasi , Osonde Osoba , Bart Kosko
- 申请人地址： US CA Los Angeles
- 专利权人： UNIVERSITY OF SOUTHERN CALIFORNIA
- 当前专利权人： UNIVERSITY OF SOUTHERN CALIFORNIA
- 当前专利权人地址： US CA Los Angeles
- 主分类号： G10L15/14
- IPC分类号： G10L15/14 ; G10L25/33 ; G10L25/36 ; G10L15/06
摘要：
A learning computer system may estimate unknown parameters and states of a stochastic or uncertain system having a probability structure. The system may include a data processing system that may include a hardware processor that has a configuration that: receives data; generates random, chaotic, fuzzy, or other numerical perturbations of the data, one or more of the states, or the probability structure; estimates observed and hidden states of the stochastic or uncertain system using the data, the generated perturbations, previous states of the stochastic or uncertain system, or estimated states of the stochastic or uncertain system; and causes perturbations or independent noise to be injected into the data, the states, or the stochastic or uncertain system so as to speed up training or learning of the probability structure and of the system parameters or the states.
摘要（中）：
学习计算机系统可以估计具有概率结构的随机或不确定系统的未知参数和状态。 该系统可以包括数据处理系统，其可以包括具有以下配置的硬件处理器：接收数据; 产生数据的随机，混乱，模糊或其他数字扰动，一个或多个状态或概率结构; 使用数据，生成的扰动，随机或不确定系统的先前状态或随机或不确定系统的估计状态的随机或不确定系统的观测和隐藏状态的估计; 并引起扰动或独立噪声注入到数据，状态或随机或不确定系统中，以加速对概率结构和系统参数或状态的训练或学习。