Awakening model training method, device and computer equipment

A training method and model technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem that the false wake-up rate cannot be applied to small-sized wake-up models, etc., so as to improve the distinguishing ability, reduce the false wake-up rate, and improve the wake-up effect. Effect

Active Publication Date: 2021-05-07
深圳市友杰智新科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a training method for wake-up models, aiming to solve the technical problem that existing methods for reducing false wake-up rates cannot be applied to small-volume wake-up models

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
  • Awakening model training method, device and computer equipment
  • Awakening model training method, device and computer equipment
  • Awakening model training method, device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0050] refer to figure 1 , the training method of the wake-up model of an embodiment of the present application, including:

[0051] S1: Extracting audio frames for the specified speech sentence in the training set, wherein the specified speech sentence belongs to any speech training sample in the training set;

[0052] S2: Input the acoustic feature matrix into the keyword detector of the first model to obtain the first spatial feature, and input the acoustic feature matrix into the encoder of the second model to obtain the second spatial feature, wherein the The first ...

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

This application relates to the field of artificial intelligence, and discloses a training method for awakening models, including: extracting audio frames from specified speech sentences in the training set to obtain an acoustic feature matrix; inputting the acoustic feature matrix into the keyword detector of the first model to obtain the first space feature, input the acoustic feature matrix into the encoder of the second model to obtain the second spatial feature, the first model is the wake-up model to be trained, and the second model is the trained noise reduction model; calculate the first spatial feature and the second spatial feature The difference of the spatial characteristics of the feature; according to the calculation method of the difference of the spatial characteristics corresponding to the specified speech sentence, calculate the difference of the spatial characteristics corresponding to all the speech sentences in the training set; Set the cross-entropy loss to form the loss function of training the wake-up model to train the wake-up model. The feature vector of the high-dimensional space is used as a knowledge distillation sample to assist in training the wake-up model and improve the wake-up effect.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to the training method, device and computer equipment of the wake-up model. Background technique [0002] How to reduce the false wake-up rate has always been the main problem to be solved in the wake-up model. The general idea starts from two aspects. On the one hand, noise processing is performed in the data set. The noise data includes data of a specific scene or as many types of noise data as possible to simulate Real scene; Usually, the increase in the amount and type of noise data means that the network has a stronger learning ability, so when processing data, a more effective network structure should be designed on the model structure to improve the learning ability of the wake-up model. On the other hand, pre-processing modules are added before wake-up, including but not limited to traditional front-end gain amplification, reverberation, array noise reduction...

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): G10L15/02G10L15/06G10L15/08G10L15/16G10L15/26G10L21/0264
CPCG10L15/02G10L15/063G10L15/08G10L15/16G10L15/26G10L21/0264G10L2015/088
Inventor 徐泓洋王广新杨汉丹
Owner 深圳市友杰智新科技有限公司
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