Full-sequence training of deep structures for speech recognition

A deep and structured technology, applied in the field of learning technology, can solve the problems of DBN learning difficulties, ineffective execution, backpropagation algorithm falling into local optimum, etc.

Active Publication Date: 2012-05-02
MICROSOFT TECH LICENSING LLC
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although DBNs generally have higher modeling power than their shallower counterparts, learning in DBNs is difficult, in part becaus

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
  • Full-sequence training of deep structures for speech recognition
  • Full-sequence training of deep structures for speech recognition
  • Full-sequence training of deep structures for speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Various techniques related to automatic speech recognition (ASR) systems will now be described with reference to the drawings, wherein like reference numerals refer to like elements throughout. Additionally, several functional block diagrams of various example systems are shown and described herein for purposes of explanation; however, it will be appreciated that functions described as being performed by particular system components may be performed by multiple components. Similarly, for example, a component may be configured to perform functions described as being performed by multiple components, and some steps in methods described herein may be omitted, reordered, or combined.

[0021] refer to figure 1 , illustrates an example system 100 that facilitates performing ASR. System 100 includes speech recognition system 102 that receives samples 104 . The samples may be words spoken (eg captured by use of a microphone) from the individual over a certain amount of time....

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 is disclosed herein that include an act of causing a processor to access a deep-structured model retained in a computer-readable medium, wherein the deep-structured model comprises a plurality of layers with weights assigned thereto, transition probabilities between states, and language model scores. The method can further include the act of jointly substantially optimizing the weights, the transition probabilities, and the language model scores of the deep-structured model using the optimization criterion based on a sequence rather than a set of unrelated frames.

Description

technical field [0001] The invention relates to language recognition technology, in particular to learning technology in deep structured models. Background technique [0002] Speech recognition has been the subject of extensive research and commercial development. For example, speech recognition systems have been incorporated into mobile phones, desktop computers, automobiles, etc. to provide specific responses to speech input provided by users. For example, in a mobile phone equipped with voice recognition technology, a user can speak the name of a contact listed on the mobile phone, and the mobile phone can initiate a call to that contact. [0003] Additionally, many companies are currently using speech recognition technology to assist customers in identifying company employees, identifying problems with products or services, and the like. [0004] Motivated in part by the requirement to exploit some similar properties in human speech generation and perception systems, r...

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
IPC IPC(8): G10L15/06G10L15/14
CPCG06K9/6296G10L15/14G06N3/084G06N3/045G06F18/29
Inventor D·俞L·邓A·S·A·穆罕默德
Owner MICROSOFT TECH LICENSING LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap