Invention Grant
- Patent Title: System for estimating parameters of a gaussian mixture model
- Patent Title (中): 用于估计高斯混合模型参数的系统
-
Application No.: US10509527Application Date: 2003-03-24
-
Publication No.: US07664640B2Publication Date: 2010-02-16
- Inventor: Christopher John St. Clair Webber
- Applicant: Christopher John St. Clair Webber
- Applicant Address: GB
- Assignee: Qinetiq Limited
- Current Assignee: Qinetiq Limited
- Current Assignee Address: GB
- Agency: McDonnell Boehnen Hulbert & Berghoff LLP
- Priority: GB0207343.5 20020328
- International Application: PCT/GB03/01244 WO 20030324
- International Announcement: WO03/083831 WO 20031009
- Main IPC: G01L15/00
- IPC: G01L15/00

Abstract:
A signal processing system is disclosed which is implemented using Gaussian Mixture Model (GMM) based Hidden Markov Model (HMM), or a GMM alone, parameters of which are constrained during its optimization procedure. Also disclosed is a constraint system applied to input vectors representing the input signal to the system. The invention is particularly, but not exclusively, related to speech recognition systems. The invention reduces the tendency, common in prior art systems, to get caught in local minima associated with highly anisotropic Gaussian components—which reduces the recognizer performance—by employing the constraint system as above whereby the anisotropy of such components are minimized. The invention also covers a method of processing a signal, and a speech recognizer trained according to the method.
Public/Granted literature
- US20060178887A1 System for estimating parameters of a gaussian mixture model Public/Granted day:2006-08-10
Information query