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

Speech recognition method, device, equipment and storage medium

A speech recognition and speech information technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as false wake-up of the dialogue system, user interruption, false wake-up, etc., to avoid false wake-up, wake-up recognition optimization, and improve user experience Effect

Active Publication Date: 2021-07-09
MOBVOI INFORMATION TECH CO LTD
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of implementing the present invention, the inventor found that the existing technology has the following defects: the user can play voice information through the smart terminal or the associated smart terminal, for example, play the audio e-book through the smart terminal or the associated smart terminal
When the voice information played contains content similar to the wake-up word, false wake-ups are prone to occur
That is, when the user does not need to wake up the dialogue system of the smart terminal, the content similar to the wake-up word in the voice information played in the environment is recognized as the wake-up word, and the dialogue system is awakened by mistake, and the dialogue system performs voice interaction, which disturbs the user

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 method, device, equipment and storage medium
  • Speech recognition method, device, equipment and storage medium
  • Speech recognition method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 1 It is a flow chart of a speech recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of recognizing speech signals. The method can be executed by a speech recognition device, and the device is composed of software and / or hardware To execute, and generally can be integrated in the terminal equipment. Terminal devices include but are not limited to computers and the like. Exemplarily, the terminal device may be a smart watch, a smart phone, a smart bracelet, a smart speaker, or a smart TV. Such as figure 1 As shown, it specifically includes the following steps:

[0027] Step 101. When the terminal device determines that the voice information to be played is about to be played during sleep, it acquires a word set corresponding to the voice information to be played.

[0028] Among them, in order to save the power of the terminal device and prolong the use time of the terminal device, when the user d...

Embodiment 2

[0044] figure 2 It is a flow chart of a speech recognition method provided by Embodiment 2 of the present invention. This embodiment optimizes step 102 on the basis of the above embodiments: the terminal device The degree of similarity is to perform wake-up word detection on the received voice information, including: when the terminal device determines whether the received voice information contains There is a voice signal corresponding to the wake-up word; when it is detected that there is a voice signal corresponding to the wake-up word in the voice information, the first matching score between the voice signal corresponding to the wake-up word and the wake-up word is obtained, and the voice signal corresponding to the wake-up word is compared with similar words. The second matching score, and comparing the first matching score and the second matching score; when the first matching score is greater than or equal to the second matching score, it is determined that the wake-u...

Embodiment 3

[0073] image 3 It is a flow chart of a voice recognition method provided by Embodiment 3 of the present invention. This embodiment optimizes step 102 on the basis of the above embodiments: the terminal device The detection of wake-up words on the received voice information includes: when the terminal device determines that the word set does not contain similar words of wake-up words and does not contain the same words of wake-up words according to the degree of similarity, it detects whether the received voice information There is a voice signal corresponding to the wake-up word; when it is detected that the voice signal corresponding to the wake-up word exists in the voice information, it is determined that the wake-up word is recognized in the voice information.

[0074] Such as image 3 As shown, the method includes:

[0075] Step 301. When the terminal device determines that the voice information to be played is about to be played during the sleep process, it acquires a...

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 embodiment of the invention discloses a voice recognition method, device, equipment and storage medium. Wherein, the method includes: when the terminal device determines that the voice information to be played is about to be played during the sleep process, then acquiring a word set corresponding to the voice information to be played, and the terminal device enables the wake-up word wake-up function in advance; the terminal device According to the degree of similarity between the set of words and a preset wake-up word, the wake-up word detection is performed on the received voice information. The technical solution of the embodiment of the present invention can specifically shield the voice information played in the environment according to the voice information to be played when performing wake-up recognition, avoid false wake-up, optimize wake-up recognition, and improve user experience.

Description

technical field [0001] Embodiments of the present invention relate to intelligent terminal technologies, and in particular to a voice recognition method, device, equipment and storage medium. Background technique [0002] With the continuous advancement of science and technology, voice control technology is becoming more and more popular. Most smart terminals basically have a dialogue system that can perform voice interaction. Through voice interaction with the dialog system of the smart terminal, the operation of the smart terminal becomes simpler and more convenient. [0003] In the implementation solution of the prior art, each time before interacting with the dialogue system, a fixed wake-up word is used to wake up the dialogue system, and the voice interaction is performed after the system enters the wake-up state. [0004] In the process of implementing the present invention, the inventor found that the prior art has the following defects: the user can play voice inf...

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): G10L15/26G10L15/20G10L21/0272G10L25/51
CPCG10L15/20G10L15/26G10L21/0272G10L25/51
Inventor 许超
Owner MOBVOI INFORMATION TECH CO LTD