Deep belief network for large vocabulary continuous speech recognition

A deep, video signal technology, used in speech recognition, speech analysis, biological neural network models, etc., can solve problems such as not making good use of hidden layers

Active Publication Date: 2012-04-11
MICROSOFT TECH LICENSING LLC
View PDF2 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, training a feed-forward ANN using only backprop

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
  • Deep belief network for large vocabulary continuous speech recognition
  • Deep belief network for large vocabulary continuous speech recognition
  • Deep belief network for large vocabulary continuous speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] 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.

[0020] 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 utilizing a microphone) from an individual over a certain amount of tim...

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 includes an act of causing a processor to receive a sample, wherein the sample is one of spoken utterance, an online handwriting sample, or a moving image sample. The method also comprises the act of causing the processor to decode the sample based at least in part upon an output of a combination of a deep structure and a context-dependent Hidden Markov Model (HMM), wherein the deep structure is configured to output a posterior probability of a context-dependent unit. The deep structure is a Deep Belief Network consisting of many layers of nonlinear units with connecting weights between layers trained by a pretraining step followed by a fine-tuning step.

Description

technical field [0001] The present invention relates to deep trust networks for large vocabulary continuous speech recognition. 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. In addition, many companies are currently using speech recognition technology to assist customers in identifying company employees, identifying problems with products or services, and the like. [0003] However, even after decades of research, the performance of automatic speech recognition (ASR) systems in real-world usage scenarios is still far from ...

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): G10L15/14G10L15/16
CPCG10L15/14G06N3/084G06N3/047G06N3/044G06N3/045
Inventor L·邓D·俞G·E·达尔
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