Multimodal disambiguation of speech recognition

A speech recognition, non-sound technology, applied in the field of speech recognition, can solve the problems of reducing the accuracy of handwriting recognition, slow handwriting typing, and large differences in handwriting styles.

Inactive Publication Date: 2007-05-16
AOL LLC A DELAWARE LLC
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] 1) Handwriting is usually slower than typing;
[0018] 2) On small devices, memory limitations reduce the accuracy of handwriting recognition; and
[0019] 3) Each person's handwriting style is very diff

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
  • Multimodal disambiguation of speech recognition
  • Multimodal disambiguation of speech recognition
  • Multimodal disambiguation of speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention provides a device and method for intelligent editing of speech recognition output, which can provide the most likely choice or hypothesis (hypotheses) according to the user's input. The speech recognition engine scores alternative hypotheses that add numerical values ​​to the information presented to the user. For example, if speech recognition provides the user with a wrong first choice hypothesis, the user would want to obtain other N-best hypotheses to modify the hypothesis returned by the recognizer. In a multimodal environment, a list of N best hypotheses from the speech recognition output can be obtained. Specifically, the list of the N best hypotheses is added to the current text menu for easy editing.

[0064] One embodiment of the invention uses both acoustic information and textual context in providing the N best hypotheses. This can be syntactically dependent or independent. That is, a language model may provide grammatical informatio...

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

The present invention provides a speech recognition system combined with one or more alternate input modalities to ensure efficient and accurate text input. The speech recognition system achieves less than perfect accuracy due to limited processing power, environmental noise, and/or natural variations in speaking style. The alternate input modalities use disambiguation or recognition engines to compensate for reduced keyboards, sloppy input, and/or natural variations in writing style. The ambiguity remaining in the speech recognition process is mostly orthogonal to the ambiguity inherent in the alternate input modality, such that the combination of the two modalities resolves the recognition errors efficiently and accurately. The invention is especially well suited for mobile devices with limited space for keyboards or touch-screen input.

Description

technical field [0001] The present invention relates to a user entering information into a system using an input device. More specifically, the present invention relates to speech recognition combined with a text input clarity system. Background technique [0002] Portable computers have become smaller and smaller over the years. The major size limiting component in the effort to create a smaller portable computer is the keyboard. A portable computer should be at least as large as a standard keyboard, if standard typewriter-sized keys are used. Mini-keyboards have been used in portable computers, but the keys of the mini-keyboards are too small to allow users to operate easily or quickly. Adding a full-size keyboard to a portable computer also prevents the computer from being truly portable. Most portable computers cannot be operated without being placed on a flat work surface that allows the user to type with both hands. A user cannot use a portable computer while movi...

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): G10L15/00G10L15/24G10L15/32
Inventor M·朗格R·埃亚德K·C·贺尔费什
Owner AOL LLC A DELAWARE 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