A computer-readable storage medium and a speech recognition speaker using the medium

A storage medium and speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as false wake-up of products, large energy consumption, and the inability of speakers to have large displacements, to ensure accuracy, reduce The effect of power consumption

Active Publication Date: 2020-12-29
广东思派康电子科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1. It is impossible to distinguish whether it is a person waking up or a machine (such as a TV) waking up, resulting in false wakeup of the product;
[0004] 2. After waking up, in order to ensure the best recognition effect, the current speakers require that the speaker cannot have a large displacement. When the speaker moves, the error rate of speech recognition will increase significantly;
[0005] 3. The current speaker voice wake-up algorithm needs to run all the time, which consumes a lot of energy consumption

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
  • A computer-readable storage medium and a speech recognition speaker using the medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention is further described in conjunction with the following examples.

[0027] A computer-readable storage medium of the present embodiment, which stores a computer program for improving the wake-up accuracy of the voice recognition speaker, and performs the following steps when the program is invoked by the processor:

[0028] The heat sensing element starts to scan the heat source. After scanning the heat source, it judges whether the heat source is a person according to the visual outline formed by the heat source, that is, by detecting external infrared radiation, and then through photoelectric conversion to form a visual outline. If it is judged that there is no one, the thermal sensing element will scan the heat source again. If it is judged that there is a person, it will be judged whether the person is within 7m of the speaker according to the energy intensity of the heat source (of course, the preset range can also be set according to actual nee...

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 computer readable storage medium and a speech recognition sound box by employing the same, and relates to the technical field of sound boxes. If a speech collection system of a sound box receives speech signals, the following steps are executed: the step 1: it is inducted whether there is a heat source or not in a preset range around the sound box, if there is a heat source, a step 2 is executed; the step 2: it is determined whether the heat source is a person or not, if yes, a step 3 is executed; and the step 3: the sound box is waken up. The computer readablestorage medium and the speech recognition sound box by employing the same can improve the wakeup accuracy of the speech recognition sound box.

Description

technical field [0001] The invention relates to the technical field of sound boxes, in particular to a computer-readable storage medium and a sound recognition sound box using the medium. Background technique [0002] At present, there are many voice wake-up speakers on the market, which can recognize different wake-up words and recognize the speaker's voice, but the products currently on the market have the following defects: [0003] 1. It is impossible to distinguish whether it is a person waking up or a machine (such as a TV) waking up, resulting in false wakeup of the product; [0004] 2. After waking up, in order to ensure the best recognition effect, the current speaker requires the speaker not to have a large displacement. When the speaker moves, the error rate of speech recognition will increase significantly; [0005] 3. The current speaker voice wake-up algorithm needs to run all the time, which consumes a lot of energy. Contents of the invention [0006] The ...

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): G10L15/22
CPCG10L15/22G10L2015/223G10L2015/226
Inventor 吴岳峰陈洪太胡中骥
Owner 广东思派康电子科技有限公司
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