Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Voice identification based on decision tree

A speech recognition and decision tree technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as spending most of the time

Inactive Publication Date: 2003-05-28
MOTOROLA INC
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Speaker-independent large-vocabulary speech recognition systems typically spend most of their time undesirably finding matching tokens

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice identification based on decision tree
  • Voice identification based on decision tree
  • Voice identification based on decision tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] see figure 1 , which shows a schematic block diagram of the speech recognition system 1, including: a statistical speech model database 110, which has an output connected to the input of the segmentation module 120 and the speech recognizer 160. Segmentation module 120 has an output connected to an input of threshold generator 130 , which has an output connected to an input of decision tree builder 140 . An output of the decision tree builder 140 is connected to an input of the decision tree memory 170 . Decision tree memory 170 has an output connected to an input of speech recognizer 160 . There is also a speech model converter 150 which has an input for receiving a speech signal. Speech model converter 150 has an output connected to one input of speech discriminator 160 .

[0039] exist figure 2 In , a method 200 of building a decision tree for processing sample signals representing speech is shown. After the start step 201, the method 200 includes a step 220 of...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method (200) is described for creating decision trees for processing a sampled signal indicative of speech. The method includes providing model sub vectors from partitioned statistical speech models of phones, the models comprising vectors of mean values and associated variance values. The method (200) then provides for statistically analyzing (230) the model sub vectors of mean values to provide projection vectors indicating directions of relative maximum variance between the sub vectors and thereafter calculating projection values (240) of the projection vectors. The potential threshold values is determined from analysis of a range of the projection values. Finally a step of creating the decision trees (270) divides the model sub vectors into groups, the groups being leaves of the tree. The decisions are based upon selected threshold values selected from the potential threshold values, the selected threshold values being selected by change in variance between said model sub vectors the variance being determined from said mean values and associated variance values. There is also described a method for speech recognition (300) that uses the decisions trees created by the method.

Description

technical field [0001] The invention relates to speech recognition. The invention is particularly useful for large vocabulary speech recognition libraries (but not limited to) based on binary decision trees to reduce the speech recognition search space. Background technique [0002] Large vocabulary speech recognition systems recognize many received uttered words. In contrast, limited vocabulary speech recognition systems are limited to a smaller number of words that can be uttered and recognized. Applications of limited-vocabulary speech recognition systems include the recognition of a small number of commands and names. [0003] The development of large-vocabulary speech recognition systems is increasing, and such large-vocabulary speech recognition systems are being used in various applications. Such speech recognition systems must be able to recognize spoken words in a responsive manner without significant delay before providing an appropriate response. [0004] Larg...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/00G10L15/08G10L15/10G10L15/12G10L15/14
CPCG10L15/10G10L15/14G10L15/08
Inventor 李恒舜
Owner MOTOROLA INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com