Information retrieval and speech recognition based on language models

A language model and speech recognition technology, applied in speech recognition, digital data information retrieval, speech analysis, etc., can solve problems such as less data, inability to adapt language models, and a large number of feeds

Inactive Publication Date: 2004-10-13
MICROSOFT TECH LICENSING LLC
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in order to accurately fit a language model, a large amount of data must be fed
However, the available data specified by the user is usually very little, and the language model cannot be quickly adapted, or a meaningful, user-specified language model cannot be generated.

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
  • Information retrieval and speech recognition based on language models
  • Information retrieval and speech recognition based on language models
  • Information retrieval and speech recognition based on language models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] figure 1and the associated discussion are intended to provide a convenient, general description of a suitable computing environment in which the invention may be implemented. Although not required, the invention will be described, at least in part, in the general context of computer-executable instructions, such as program modules, being executed by a personal computer. Generally, a program module includes commonly used programs, objects, elements, or data structures, etc., used to perform specified tasks or implement specified abstract data types, etc. Furthermore, those skilled in the art will appreciate that the present invention may be implemented with other computer system configurations, including handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers and more. The invention may also be practiced in distributed computing environments where tasks are performed by remote ...

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 language model is used in a speech recognition system which has access to a first, smaller data store and a second, larger data store. The language model is adapted by formulating an information retrieval query based on information contained in the first data store and querying the second data store. Information retrieved from the second data store is used in adapting the language model. Also, language models are used in retrieving information from the second data store. Language models are built based on information in the first data store, and based on information in the second data store. The perplexity of a document in the second data store is determined, given the first language model, and given the second language model. Relevancy of the document is determined based upon the first and second perplexities. Documents are retrieved which have a relevancy measure that exceeds a threshold level.

Description

technical field [0001] The present invention relates to speech recognition and information retrieval, more specifically, the present invention relates to a speech recognition system that uses information retrieval technology to match a certain language model and a speech recognition language model that uses a speech recognition language model to retrieve related documents information retrieval technology. Background technique [0002] Generally speaking, information retrieval is a process of finding and retrieving user-related information from a large amount of information storage. In the process of performing information retrieval, it is important to retrieve all the information that the user needs (that is, completeness is important), and it is also important to limit the retrieved information that is irrelevant to the user (that is, selectivity is also important). These aspects are usually defined in terms of recall (completeness) and precision (selectivity). In many in...

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 Patents(China)
IPC IPC(8): G10L15/06G06F17/30G10L15/183G10L15/197G10L15/22
CPCG10L15/197G06F17/30687G10L15/183Y10S707/99934G06F16/3346G10L15/06
Inventor 米林德·V·迈哈简黄学东
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