Speech recognition method and device for target equipment, equipment and storage medium

A target device, speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as difficult to solve, crosstalk between command words, etc., to achieve the effect of improving accuracy, reducing crosstalk rate, and powerful feature learning ability

Pending Publication Date: 2022-03-11
IFLYTEK CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a voice recognition method, device, device and storage medium for a target device, which is used to solve the gap between different command words in t

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
  • Speech recognition method and device for target equipment, equipment and storage medium
  • Speech recognition method and device for target equipment, equipment and storage medium
  • Speech recognition method and device for target equipment, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0091] In order to make the objects, technical solutions, and advantages of the present invention, the technical solutions in the present invention will be apparent from the drawings of the present invention, and it will be described in connection with the drawings of the present invention. , Not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained without creative labor are not made in the premise of creative labor.

[0092] The specification and claims of the invention and the terms "first", "second", "second", and the like in the above drawings are used to distinguish similar objects without having to describe a particular order or award order. It should be understood that the data such as use can be interchangeable in appropriate, so that the embodiments described herein can be implemented in the order other than the content illustrated or described herein.

[0093] With the increasing mature of artificial intelligence relat...

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 provides a speech recognition method and device for target equipment, equipment and a storage medium. The method comprises the steps that an audio signal is acquired, acoustic features of the audio signal are obtained, the acoustic features are input into a first acoustic model, and phoneme-level features and phoneme-level probability vectors associated with the phoneme-level features are obtained; if the current working mode of the target equipment is a wake-up mode, inputting the phoneme-level probability vector into a preset decoder to recognize a wake-up word, and converting the working mode of the target equipment into a command word mode under the condition that the wake-up word is recognized; and if the current working mode of the target equipment is a command word mode, inputting the phoneme-level features into a second acoustic model so as to trigger the target equipment to execute an action corresponding to a command word when the command word is recognized. According to the method, the problem of crosstalk caused by unequal length comparison when command words with different lengths pass through a decoding network at present can be solved, and the correctness of command word recognition is effectively improved.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a voice recognition method, device, equipment and storage medium for target equipment. Background technique [0002] Existing voice wake-up and command word methods generally include two parts: an acoustic model and a decoding network. After extracting the acoustic features of the voice data, input the pre-built acoustic model to obtain the posterior probability, and then input the posterior probability into the decoding network to obtain each item in the network. Acoustic scores of the wake-up word, command word path, and absorption path, and finally compare the acoustic scores of each path, and the path with the highest score is the recognition result. However, this method will cause the problem of unequal length comparison when command words of different lengths pass through the decoding network, resulting in serious crosstalk between different command words ...

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): G10L15/02G10L15/06G10L15/08G10L15/16G10L15/26
CPCG10L15/02G10L15/063G10L15/08G10L15/16G10L15/26G10L2015/025
Inventor 徐文娜孙磊申凯
Owner IFLYTEK 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