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

Vocoder-based voice recognizer

A technology of speech recognition and vocoder, which is applied in the field of speech recognition, and can solve the problems of increasing the cost of mobile phones

Inactive Publication Date: 2000-11-15
ART ADVANCED RECOGNITION TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This adds a lot of cost to the mobile phone

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
  • Vocoder-based voice recognizer
  • Vocoder-based voice recognizer
  • Vocoder-based voice recognizer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] There are many speech compression algorithms, the most commonly used are those based on linear predictive coding (LPC). The applicants of the present invention have realized that since most speech recognition algorithms utilize linear predictive coding analysis to extract parameters from the speech signal, elements of the compressed speech signal can be provided to the speech recognizer to significantly reduce the speech recognizer's performance. Analysis volume. Accordingly, the present invention is a vocoder-based speech recognizer implemented in a microcontroller or CPU of a cellular mobile telephone, as described in detail below with reference to FIGS. 5, 6 and 7. FIG.

[0032] Linear predictive analysis:

[0033] The working principle of the LPC-based vocoder 16 is briefly described below. A general discussion of speech coding, including a more detailed description of linear predictive coding than this description, can be found in Andreas S. Spanias in Proceeding...

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 vocoder based voice recognizer recognizes a spoken word using linear prediction coding based vocoder data without completely reconstructing the voice data. The recognizer generates at least one energy estimate per frame of the vocoder data (60) and searches for word boundaries in the vocoder data (64) using the associated energy estimates. If a word is found (66), the linear prediction coding word parameters are extracted (68) from the vocoder data associated with the word and recognition features are calculated (70) from the extracted linear prediction coding word parameters. Finally, the recognition features are matched with previously stored recognition features of other words (40), thereby recognizing the spoken word.

Description

field of invention [0001] The present invention relates generally to speech recognizers, and to speech recognizers using linear predictive coding (LPC) vocoder data as input. Background of the invention [0002] Speech recognizers are very familiar to everyone in this field, and they are used in many places. For example, voice recognition is used in command and control applications for mobile devices, computer dictaphones, children's toys, and car phones. In all of these systems, the speech signal is digitized and then parameterized. The parameterized input signal is compared to a reference parameterized signal whose pronunciation is known. The relevant utterance of the reference signal that best matches the input signal is the recognized utterance. [0003] The voice recognition system has its special purpose in the voice dialing system. When the user speaks the name of the person he wants to call, the voice recognition system recognizes the name from the reference table...

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): G10L15/10G10L15/02G10L15/30G10L19/04G10L25/78
CPCG10L19/04G10L2025/783G10L15/02G10L15/30G10L13/00
Inventor 耶胡达·赫什科维茨加布里埃尔·伊兰
Owner ART ADVANCED RECOGNITION TECH
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