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

Compensation device and method for voice recognition equipment

A technology of speech recognition equipment and compensation device, which is applied in speech recognition, speech analysis, instruments, etc., and can solve problems such as insufficient speed

Inactive Publication Date: 2011-11-09
SAMSUNG ELECTRONICS CO LTD +1
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For some practical ASR based on portable devices, compensation for speaker and device must be performed in different stages, and MLLR will not be fast enough for time-varying environments

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
  • Compensation device and method for voice recognition equipment
  • Compensation device and method for voice recognition equipment
  • Compensation device and method for voice recognition equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Embodiments of the present invention will now be described in detail, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like parts throughout.

[0025] figure 1 is a block diagram showing a compensation apparatus for a speech recognition device according to an exemplary embodiment of the present invention.

[0026] It should be understood that the compensation device according to the exemplary embodiment of the present invention can be used in any suitable speech recognition device, and at the same time, the speech recognition device needs to be embedded in various speech recognition-related applications (such as information retrieval, voice webpage search, etc.) , voice input, etc.), such as mobile phones, personal digital assistants (PDAs), etc., but the present invention is not limited thereto.

[0027] Such as figure 1 As shown, the compensation apparatus for a speech recognition device according to an exempla...

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 invention provides a compensation device and a compensation method for voice recognition equipment. The compensation device comprises a model training module, a global compensation module, a target compensation module and an environment compensation module, wherein the model training module trains a preset acoustic model by using an expectation maximization algorithm and outputs an acoustic model of an unspecific speaker; the global compensation module compensates a specific domain and a specific device which influence acoustic data by using the acoustic model and outputs a globally adaptive acoustic model; the target compensation module compensates change of a specific speaker by using the globally adaptive acoustic model and outputs an acoustic model adapting to the speaker; and the environment compensation module compensates change of a specific environment by using the acoustic model adapting to the speaker and outputs an acoustic model adapting to the environment.

Description

technical field [0001] The present invention relates to a compensation device and method, more particularly, to a compensation device and method for speech recognition equipment. Background technique [0002] Over the past few decades, automatic speech recognition (ASR) has achieved good results in clean environments. In such an environment, several non-specific speaker large vocabulary continuous speech recognition (Large Vocabulary Continuous Speech Recognition, LVCSR) systems have achieved word error rates between 5% and 10%. However, in real noisy environments, the performance of ASR systems degrades significantly. Robust automatic speech recognition techniques against sound variations in the device, speaker, channel, background, etc. have become a key technique for practical ASR systems. [0003] Generally speaking, a practical ASR system needs to compensate for the sound changes in the following three parts: data in a specific domain or a specific device; speakers of...

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): G10L15/20G10L15/18
Inventor 苏腾荣朱璇张华严基完
Owner SAMSUNG ELECTRONICS CO LTD
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