End-to-end wake-up word detection method and device

A detection method and wake-up word technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of wake-up word detection rate to be improved, false wake-up, etc., to suppress false wake-up phenomenon, improve accuracy, and improve detection rate effect

Pending Publication Date: 2020-08-18
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This detection method has at least the following disadvantages: the detection rat...

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
  • End-to-end wake-up word detection method and device
  • End-to-end wake-up word detection method and device
  • End-to-end wake-up word detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0095] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0096] Embodiments of the present invention provide an end-to-end wake-up word detection method and device. According to the posterior probability of each target pronunciation unit output by the acoustic model, when performing dynamic time planning, insert virtual mute nodes before and after the target pronunciation unit, The cumulative probability of each target pronunciation unit is calculated frame by frame, and then an optimal path is determined according to the cumulative probability, and a wake-up word detection result is determined according to the optimal path.

[0097] The training process of the acoustic model in the embodiment of the present invention will firstly be described in detail below.

[0098...

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 an end-to-end wake-up word detection method and device. The method comprises the steps of receiving to-be-detected voice; sequentially extracting acoustic features of each voice frame in the to-be-detected voice; inputting the extracted acoustic features into a pre-constructed acoustic model to obtain a posterior probability of a target pronunciation unit in each voice frame output by the acoustic model; taking each target pronunciation unit as a node, and inserting virtual mute nodes in front of and behind the target pronunciation unit to obtain a target-time relationship matrix; calculating the cumulative probability of each node in the target-time relation matrix frame by frame; determining an optimal path according to the cumulative probability of each node in the matrix; and determining a wake-up word detection result according to the optimal path. According to the invention, the accuracy of a detection result can be improved, and the false awakening rate is reduced.

Description

technical field [0001] The invention relates to the technical field of voice wake-up, in particular to an end-to-end wake-up word detection method and device. Background technique [0002] The voice wake-up technology means that when the smart device detects the user's specific voice (usually the set wake-up word) in the sleep state, the device enters the waiting state, and then enters the voice intelligent interaction process. Voice wake-up has a wide range of applications, such as robots, speakers, cars, etc. The main indicators for evaluating the voice wake-up effect are wake-up rate and false wake-up rate, and the performance of the decoder in the speech recognition process plays a key role in it. [0003] At present, the wake-up detection method used by most smart devices is a wake-up word detection method based on end-to-end technology. In the traditional end-to-end model, the output of the acoustic model in the decoder generally corresponds to the pronunciation unit...

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
IPC IPC(8): G10L15/05G10L15/06G10L15/08G10L15/22
CPCG10L15/05G10L15/06G10L15/08G10L15/22G10L2015/088G10L2015/223
Inventor 解传栋胡博刘忠亮唐文琦
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT 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