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

Method and device for recognizing voices

A speech recognition and speech data technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as poor use effect, insignificant improvement effect, and low recognition rate.

Active Publication Date: 2014-08-06
HUAWEI DEVICE CO LTD
View PDF9 Cites 86 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, voice assistant software usually works relatively well in quiet environments such as offices, but it does not work well in noisy environments (such as in vehicle environments); the industry generally adopts software noise reduction methods to improve speech recognition rate, but the improvement effect is not obvious, and sometimes even reduces the recognition rate

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
  • Method and device for recognizing voices
  • Method and device for recognizing voices
  • Method and device for recognizing voices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] figure 1 It is a flow chart of a speech recognition method provided by Embodiment 1 of the present invention.

[0041] Such as figure 1 As shown, Embodiment 1 of the present invention provides a method for speech recognition that may specifically include:

[0042] S100, acquiring voice data;

[0043] The user starts the voice recognition software such as the voice assistant on the device, and obtains the voice data input by the user through the microphone. It should be understood that the voice data may not be input by a user, but may also be input by a machine, including any data containing information.

[0044] S101. Acquire a confidence value according to the voice data.

[0045] The degree of confidence refers to the degree to which a specific individual believes in the truth of a specific proposition. In the embodiment of the present invention, it is the degree to which the device believes in the authenticity of the voice data recognition result. That is, the...

Embodiment 2

[0062] image 3 It is a flow chart of another implementation manner of a speech recognition method provided by Embodiment 2 of the present invention.

[0063] Embodiment 2 of the present invention is described on the basis of Embodiment 1 of the present invention. Such as image 3 As shown, in step S102 in Embodiment 1, the noise scene specifically includes: noise type; noise magnitude.

[0064] The noise type refers to the noise environment in which the user inputs voice data, that is, it can be understood as whether the user is in a noise environment on the road, in an office, or in a vehicle.

[0065] The noise level represents the level of noise in the noise environment where the user is inputting voice data at that time. Optionally, the noise size includes: signal-to-noise ratio and noise energy level. The signal-to-noise ratio is the ratio of voice data to noise data power, often expressed in decibels. Generally, the higher the signal-to-noise ratio, the smaller the ...

Embodiment 3

[0112] Figure 4 It is a flow chart of another implementation manner of a speech recognition method provided by Embodiment 3 of the present invention.

[0113] This embodiment is described on the basis of Embodiment 1, as Figure 4 As shown, the step S103 method of embodiment 1 specifically includes:

[0114] S1031. Acquire a confidence threshold corresponding to the noise scene according to the correspondence between the pre-stored confidence threshold experience data and the noise scene.

[0115] After acquiring the noise scene where the speech data is located, the confidence threshold corresponding to the noise scene may be acquired according to the correspondence between the pre-stored confidence threshold empirical data and the noise scene. That is, the confidence threshold can be obtained according to the corresponding relationship between the noise type and noise size in the noise scene and the empirical data of the confidence threshold obtained through a large number...

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

Embodiments of the present invention provide a voice identification method, which includes: obtaining voice data; obtaining a confidence value according to the voice data; obtaining a noise scenario according to the voice data; obtaining a confidence threshold corresponding to the noise scenario; and if the confidence value is greater than or equal to the confidence threshold, processing the voice data. An apparatus is also provided. The method and apparatus that flexibly adjust the confidence threshold according to the noise scenario greatly improve a voice identification rate under a noise environment.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of speech processing, and in particular, to a speech recognition method and device. Background technique [0002] Users generally use voice assistant software for voice recognition on terminal devices such as mobile phones. The process of voice recognition with software such as voice assistants is that the user starts the voice assistant software to obtain voice data; the voice data is sent to the noise reduction module for noise reduction processing; the voice data after noise reduction processing is sent to the voice recognition engine; the voice recognition engine Return the recognition result to the voice assistant; in order to reduce misjudgment, the voice assistant judges the correctness of the recognition result according to the confidence threshold, and then presents it. [0003] At present, voice assistant software usually works relatively well in quiet environments such as 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): G10L15/20
CPCG10L25/84G10L25/24G10L15/08G10L15/20
Inventor 蒋洪睿王细勇梁俊斌郑伟军周均扬
Owner HUAWEI DEVICE 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