Voice wake-up method and device, medium and equipment
A voice wake-up and device technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problem of low success rate of voice wake-up
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044] Embodiment 1 of the present invention provides a voice wake-up method, the step flow of the method can be as follows figure 1 shown, including:
[0045] Step 101, receiving a voice signal.
[0046] In this step, a voice signal used by the user to wake up the intelligent voice interaction device may be received.
[0047] Step 102, compare.
[0048] In this step, the received voice signal may be compared with the pre-stored voice signal including keywords.
[0049] That is, in this embodiment, the user is required to input a voice signal including keywords in advance, for example, small cells.
[0050] Comparing the received speech signal with the pre-saved speech signal including keywords, it can be understood that the speech feature is extracted from the received speech signal, and the speech feature can be but not limited to spectrum or cepstral coefficient The pre-saved speech feature models corresponding to speech signals including keywords are compared to obtain...
Embodiment 2
[0062] Embodiment 2 of the present invention provides a voice wake-up method, and the step flow of the method can be as follows figure 2 shown, including:
[0063] Step 201, receiving a voice signal.
[0064] In this step, a voice signal used by the user to wake up the intelligent voice interaction device may be received.
[0065] Step 202, performing comparison.
[0066] The voice signal received for the first time in the wake-up process of this round may be referred to as voice segment 1 . Comparing the speech segment 1 with the pre-saved speech signal including keywords, the obtained similarity rate can be represented by ρ1.
[0067] Step 203, wake up.
[0068] If ρ1>=α, at this time, it can be considered that the environmental noise is small or the wake-up sound source is close, and the smart voice interactive device can be directly triggered to enter the wake-up state. The smart voice interactive device wakes up successfully, and this process ends, ending the current...
Embodiment 3
[0089] Embodiment 3 of the present invention provides a voice wake-up device, the structure of which can be as follows image 3 shown, including:
[0090] Receiving module 11 is used for receiving speech signal;
[0091] Comparison module 12 is used for comparing the speech signal received by the receiving module with the pre-saved speech signal including keywords;
[0092]The wake-up module 13 is used for if the similarity rate obtained by the comparison module comparison is lower than the first threshold value set, but not lower than the second threshold value set, and the number of times of comparison does not reach the set number of times, then prompting needs Continue to wake up, and trigger the receiving module to receive voice signals again until the number of comparisons reaches the set number of times, triggering the intelligent voice interaction device to enter the wake-up state.
[0093] The wake-up module 13 is also configured to trigger the intelligent voice int...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.
