Unlock instant, AI-driven research and patent intelligence for your innovation.

A voice recognition method and electronic device

A technology of speech recognition and electronic equipment, applied in the field of information processing, can solve problems such as the inability to meet the speech environment, and achieve the effect of accurate results

Active Publication Date: 2021-01-15
LENOVO (BEIJING) LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitations of its CPU computing power and storage space, DSP cannot meet various complex voice 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
  • A voice recognition method and electronic device
  • A voice recognition method and electronic device
  • A voice recognition method and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] The embodiment of the present invention provides a voice recognition method, such as figure 1 shown, including:

[0023] Step 101: collecting audio information including voice information, and obtaining environmental sound information in the audio information;

[0024] Step 102: Based on the level of the environmental sound, determine the matching parameters of speech recognition corresponding to the environmental sound;

[0025] Step 103: Perform voice recognition on the collected voice information based on the matching parameters of the voice recognition.

[0026] The solution provided in this embodiment can be applied to mobile terminals, such as smart phones, tablet computers, and the like. This solution first collects the voice information that can be collected by the current smart phone, and then analyzes the environmental sound information in it, for example, the noise in it, and identifies the currently collected voice information based on the matching paramet...

Embodiment 2

[0041] The embodiment of the present invention provides a voice recognition method, such as figure 1 shown, including:

[0042] Step 101: collecting audio information including voice information, and obtaining environmental sound information in the audio information;

[0043] Step 102: Based on the level of the environmental sound, determine the matching parameters of speech recognition corresponding to the environmental sound;

[0044] Step 103: Perform voice recognition on the collected voice information based on the matching parameters of the voice recognition.

[0045] The solution provided in this embodiment can be applied to mobile terminals, such as smart phones, tablet computers, and the like. This solution first collects the voice information that can be collected by the current smart phone, and then analyzes the environmental sound information in it, for example, the noise in it, and identifies the currently collected voice information based on the matching paramet...

Embodiment 3

[0087] An embodiment of the present invention provides an electronic device, such as Figure 4 shown, including:

[0088] The collection unit 41 is used to collect audio information including voice information, and obtain environmental sound information in the audio information;

[0089] A matching unit 42, configured to determine a matching parameter for speech recognition corresponding to the environmental sound based on the level of the environmental sound;

[0090] The recognition unit 43 is configured to perform speech recognition on the collected speech information based on the speech recognition matching parameters.

[0091] In this scheme, the matching unit 42 is used for the noise of the ambient sound is relatively strong noise, and selects relatively strict speech recognition matching parameters with matching conditions;

[0092] The noise of the ambient sound is relatively weak noise, and the speech recognition matching parameters with relatively loose matching co...

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 discloses a speech recognition method and an electronic device. The method includes the following steps that: audio information containing speech information is collected, so that ambient sound information in the audio information can be obtained; and the matching parameters of speech recognition corresponding to ambient sound are determined on the basis of the level of the ambient sound; and speech recognition is performed on the collected audio information on the basis of the matching parameters of speech recognition.

Description

technical field [0001] The invention relates to information processing technology, in particular to a voice recognition method and electronic equipment. Background technique [0002] As technology advances, the use of voice commands (voice control systems) on smart devices is becoming more and more popular. Their advantage is that the device is controlled using voice commands without the user needing direct contact with the smart device being controlled. Speech Recognition (ASR) and related algorithms can effectively distinguish the voice commands input by the user from the environmental noise. At present, the most advanced voice technology can use DSP for Keyword Spotting. After the keyword spotting is activated, the DSP can wake up the AP of the mobile device and wake up the control system of the voice command. However, due to the limitations of its CPU computing power and storage space, DSP cannot meet various complex voice environments. Contents of the invention [...

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): G10L15/22G10L15/26G10L21/0208G10L25/51G10L25/60
CPCG10L15/222G10L15/26G10L21/0208G10L25/51G10L25/60
Inventor 陈实
Owner LENOVO (BEIJING) LTD