False wake-up audio acquisition method, system and device and storage medium

An audio collection, false wake-up technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of difficult one-to-one reproduction, long audio time, low efficiency, etc., to achieve shortened time, large throughput, and improved The effect of precision

Pending Publication Date: 2022-01-14
深聪半导体(江苏)有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) From the perspective of controllable test process and easy access to data, the test is usually carried out in the audio laboratory through simulation restoration, but this test method is somewhat different from the real scene, and it is difficult to reproduce one by one
[0006] (2) During the test, it takes a long time to record the audio, but the audio time is too long, and the technician needs to combine the test results to find the abnormal audio and then analyze and optimize it, resulting in low efficiency

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
  • False wake-up audio acquisition method, system and device and storage medium
  • False wake-up audio acquisition method, system and device and storage medium
  • False wake-up audio acquisition method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Reference attached figure 1 As shown, the embodiment of the present application provides a false wake-up audio collection method, and the method includes the following steps.

[0047] Step S100: Receive and store ambient audio.

[0048] Wherein, in step S100, the sound source of the received and stored ambient audio is the ambient audio generated in the actual scene, or the ambient audio of various places simulated by the audio playback device.

[0049] Step S200: Receive multiple wake-up logs. The wake-up log is configured to use multiple identical devices with voice recognition functions to generate multiple wake-up logs after performing wake-up operations on the ambient audio of the same sound source in the same environment according to the preset trigger wake-up strategy.

[0050]The device in step S200 can be understood as any AI voice product with voice recognition function on the market, of course it is not limited to the product, and can also be the main contr...

Embodiment 2

[0066] refer to Figure 3-4 As shown, the embodiment of the present application provides a false wake-up audio collection system, which adopts any one of the false wake-up audio collection methods in Embodiment 1. The system includes: a host 110, a sound source 140, a radio device 130, and a voice recognition system. Multiple voice recognition devices 120 with the same function; the host 110 is connected to the voice recognition device 120 through the communication serial port, and connected to the radio device 130 through the audio port. The sound source 140 is configured to output ambient audio. The sound receiving device 130 is configured to record the ambient audio in real time and transmit the ambient audio to the host 110 . The voice recognition device 120 is configured to synchronously collect and recognize ambient audio from the same sound source 140, perform a wake-up operation based on a preset trigger wake-up strategy, generate multiple wake-up logs, and transmit t...

Embodiment 3

[0076] refer to Figure 7-8 As shown, the embodiment of the present application provides a false wake-up audio collection device, using any one of the false wake-up audio collection methods in Embodiment 1, the device includes:

[0077] The ambient audio acquisition module 210 is configured to control multiple microphones 320 to synchronously collect ambient audio from the same sound source 310 in the same environment through corresponding sound pickup holes.

[0078] The wake-up log acquisition module 220 is configured to control multiple identical speech recognizers with a speech recognition function, perform wake-up operations on ambient audio respectively according to a preset trigger wake-up strategy, and extract multiple wake-up logs generated. Wherein, the microphone 320 is paired with the speech recognizer one by one. A microphone can be understood as a microphone.

[0079] The false wake-up audio extraction module 230 is configured to combine the wake-up log into 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 invention discloses a false wake-up audio acquisition method, system and device and a storage medium. The method comprises the following steps: S100, receiving and storing environment audio; S200, receiving a plurality of wake-up logs, wherein the wake-up logs are configured to be a plurality of wake-up logs generated after a plurality of processors with voice recognition functions are used for executing wake-up operation on the environment audio of the same sound source in the same environment according to a preset wake-up triggering strategy; and S300, based on the same time period in the time sequence, according to a preset false wake-up strategy, combining the multiple wake-up logs into a data source for analysis and judgment, and according to a judgment result, extracting each segment of audio data causing false wake-up from the environment audio. By adopting the false wake-up audio obtained by the method, the audio duration is shortened, the audio occupied space is reduced, the training data volume is increased, and the precision of the recognition result is improved.

Description

technical field [0001] The present invention relates to the technical field of audio data collection, in particular to a false wakeup audio collection method, system, device and storage medium. Background technique [0002] In addition to the wake-up rate and recognition rate, the performance indicators of AI voice products (AI, Artificial Intelligence, artificial intelligence) also include the false wake-up rate. For product performance optimization, a large amount of environmental audio is usually collected in advance and input to the model to be optimized for training. to improve the corresponding indicators. Wherein, the ambient audio may be various types of noises that may appear in a real scene and their superposition. [0003] Usually these performance indicators are tested in the sound laboratory, for example, by playing various noises. However, it is impossible to realize fully automatic acquisition of various types of noise, and only large-scale long-term simulat...

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): G10L15/06G10L15/22
CPCG10L15/063G10L15/22G10L2015/223
Inventor 王年
Owner 深聪半导体(江苏)有限公司
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