Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Speech recognition-based control method, device and electronic equipment

A technology of speech recognition and control method, which is applied in speech recognition, speech analysis, data exchange through path configuration, etc., which can solve problems such as inconvenient use, inaccurate recognition, and unhumanized system design, and alleviate the high error rate , the effect of reducing the probability of false triggering

Pending Publication Date: 2018-02-23
HANGZHOU CONGPU INTELLIGENT TECH CO LTD
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current smart home products based on speech recognition still have problems such as inconvenient use, inaccurate recognition, unhumanized system design, high cost, and need to be recognized through the cloud, which affects the further promotion of speech recognition products
[0003] For the above problems, no effective solution has been proposed

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
  • Speech recognition-based control method, device and electronic equipment
  • Speech recognition-based control method, device and electronic equipment
  • Speech recognition-based control method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] According to an embodiment of the present invention, an embodiment of a control method based on speech recognition is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0026] figure 1 is a flow chart of a control method based on speech recognition according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0027] Step S102, when the smart home device is in a wake-up state, collect a first voice signal, wherein the first voice signal carries first voice information;

[0028] In the embodiment of the present invention, before controlling the smart home device, it is necessary to wake up the smart ho...

Embodiment approach 1

[0048] After the voice signal collector acquires the second voice signal, it judges whether the second voice signal is Mandarin, wherein the processor can determine the second voice signal by judging the degree of similarity between the second voice signal and Mandarin Whether it is Mandarin. If it is determined that the second voice signal is Mandarin, the second voice information carried in the second voice signal is compared with the wake-up word in wake-up phrase 1, wherein wake-up phrase 1 is a wake-up word in Mandarin.

[0049] If it is judged that the second speech signal is not Mandarin, then determine the region information to which the second speech signal belongs; wherein, the degree of similarity between the second speech signal and each dialect can be calculated respectively to determine the region to which the second speech signal belongs information; in addition, the second voice signal can also be used as the input of the target neural network, so that the targ...

Embodiment approach 2

[0054] In the embodiment of the present invention, the user can set the recognition mode of the smart home device, for example, set the recognition mode of the smart home device to a Mandarin recognition mode or a dialect recognition mode. Wherein, the user can manually set the recognition mode, and can also set the recognition mode by voice, which is not specifically limited.

[0055] After the recognition mode of the smart home device is set, the voice signal collector of the smart home device can collect the voice signal (ie, the second voice signal) sent by the user. Then, the speech information carried by the speech signal is recognized according to the recognition mode set above. Further, a second control instruction is generated according to the recognition result, so as to control the smart home device to perform a corresponding target action according to the second control instruction. A specific example will be described below to introduce the second implementation ...

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 speech recognition-based control method and device, and electronic equipment, and relates to the intelligent control technical field; the method comprises the following steps:gathering a first voice signal when the intelligent household equipment is awakened, wherein the first voice signal carries the first voice information; determining whether the first voice information is a word in an execution phrase or not, wherein the execution phrase comprises at least one execution word obtained in pre-training, and each execution word is matched with one target motion; if yes, forming a first control order according to the first voice information, controlling the intelligent household equipment to execute the corresponding target motion according to the first control order, thus alleviating the problems in the prior art that existing methods and devices are high in speech recognition error rates.

Description

technical field [0001] The present invention relates to the technical field of intelligent control, in particular to a voice recognition-based control method, device and electronic equipment. Background technique [0002] With the continuous promotion of the concept of the Internet of Things, the continuous development of related technologies of the Internet of Things and the continuous reduction of the production cost of the supporting products of the Internet of Things. More and more IoT products have been put on the market. As an important branch of the IoT industry, the smart home industry has also begun to enter the home life of ordinary people. The way of controlling equipment through traditional wall panels or handheld terminals is increasingly unable to meet the needs of users. Products based on speech recognition technology, along with the continuous innovation and development of speech technology, and the continuous improvement of practicability, are more and more...

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): G10L15/22H04L12/28
CPCG10L15/22G10L2015/223H04L12/282
Inventor 夏春波金晖
Owner HANGZHOU CONGPU INTELLIGENT TECH CO LTD
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
Eureka Blog
Learn More
PatSnap group products