Far field voice awakening method and equipment

A voice wake-up and device technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problems of increased false recognition of voice wake-up, high false wake-up, limited computing power and storage capacity, etc., to improve user experience and reduce error The effect of arousal rate

Active Publication Date: 2017-12-12
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, whether it is based on the front-end audio signal processing chip or the main processor-based offline wake-up recognition engine, it is limited by the computing power and storage capacity of the chip, resulting in a relatively simple acoustic model for offline recognition, which reduces the performance of the voice wake-up engine. Causes an increase in false recognition of voice wake-up, especially in a noisy environment, the probability of false wake-up will be higher

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
  • Far field voice awakening method and equipment
  • Far field voice awakening method and equipment
  • Far field voice awakening method and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] figure 1 It is a flow chart of the far-field voice wake-up method provided by Embodiment 1 of the present invention. This embodiment is applicable to far-field voice wake-up devices, such as smart phones, smart speakers, and smart TVs. This method can be woken up by far-field voice equipment to perform. Such as figure 1 As shown, the method specifically includes:

[0021] S110. The front-end audio signal processing chip acquires at least one voice signal among the multiple voice signals picked up by the microphone array, and determines whether the at least one voice signal is a voice wake-up signal.

[0022] In this embodiment, when a voice signal is detected, the microphone array in the far-field voice wake-up device picks up the voice signal to obtain multiple voice signals. The voice wake-up engine in the front-end audio signal processing chip obtains one or more voice signals from multiple voice signals, and uses the preset acoustic model to determine whether the...

Embodiment 2

[0039] In this embodiment, on the basis of the first embodiment, step S110 and step S120 are optimized. figure 2 It is a flow chart of the far-field voice wake-up method provided in Embodiment 2 of the present invention, as figure 2 As shown, the method specifically includes:

[0040] S210. The front-end audio signal processing chip acquires at least one voice signal among the multiple voice signals picked up by the microphone array.

[0041] S220. The front-end audio signal processing chip performs echo cancellation processing on at least one voice signal, performs noise reduction processing on the echo-canceled at least one voice signal according to a preset frequency range, and determines whether the at least one voice signal is a voice wake-up signal.

[0042] In this embodiment, before the front-end audio signal processing chip determines whether at least one voice signal is a voice wake-up signal, echo cancellation processing can be performed on at least one voice sig...

Embodiment 3

[0050] image 3 It is a schematic structural diagram of the far-field voice wake-up device in Embodiment 3 of the present invention. Such as image 3 As shown, the far-field voice wake-up device includes: a microphone array 310 , a front-end audio signal processing chip 320 and a main processor 330 . in,

[0051] The microphone array 310 picks up multiple voice signals;

[0052] The front-end audio signal processing chip 320 acquires at least one voice signal in the multi-channel voice signal, and determines whether the at least one voice signal is a voice wake-up signal;

[0053] The main processor 330 acquires at least two voice signals in the multi-channel voice signals, and determines whether the at least two voice signals are voice wake-up signals according to the multi-channel voice wake-up recognition model, wherein the multi-channel voice wake-up recognition model is based on the multi-channel voice wake-up recognition model in advance. The wake-up sample signal is...

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 far field voice awakening method and equipment, wherein the far field voice awakening method comprises the following steps: a front end audio signal processing chip acquires at least one voice signal in multiple voice signals picked up by a microphone array and determines whether the least one voice signal is a voice awakening signal or not; a primary processor acquires at least two voice signals in the multiple voice signals and determines whether the at least two voice signals are voice awakening signals or not according to a multiple voice awakening and recognizing model; and if the least one voice signal is the voice awakening signal and the at least two voice signals are voice awakening signals, the primary processor controls to execute an awakening operation. Based on the front end audio processing chip and the primary processor, the voice awakening signals are recognized twice for the multiple voice signals picked up by the microphone array, so that the mistaken awakening rate is reduced greatly and the user experience is enhanced.

Description

technical field [0001] Embodiments of the present invention relate to a voice wake-up technology, in particular to a far-field voice wake-up method and device. Background technique [0002] With the rapid development of voice recognition technology, the application of voice wake-up technology is becoming more and more common. Far-field voice wake-up technology. [0003] There are two implementations of the existing far-field voice wake-up technology, one is the implementation of voice wake-up based on the front-end audio signal processing chip (usually an audio-specific DSP), and the other is the voice wake-up based on the main processor (CPU). Method to realize. However, whether it is based on the front-end audio signal processing chip or the main processor-based offline wake-up recognition engine, it is limited by the computing power and storage capacity of the chip, resulting in a relatively simple acoustic model for offline recognition, which reduces the performance of...

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 Applications(China)
IPC IPC(8): G10L15/22G10L15/06G10L15/26
CPCG10L15/06G10L15/063G10L15/22G10L15/26
Inventor 耿雷
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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
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