Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech training method and device, speech recognition method and device, electronic equipment and storage medium

A voice training and electronic equipment technology, applied in voice recognition, voice analysis, instruments, etc., can solve the problems of unusable voice recognition technology and low accuracy rate, so as to improve the accuracy rate, recognition accuracy rate, and voice recognition accuracy rate Enhanced effect

Pending Publication Date: 2022-06-24
BEIJING XIAOMI PINECONE ELECTRONICS CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for people with language barriers such as cerebral palsy and slurred speech, the accuracy of recognizing the speech of such people is extremely low, and the current speech recognition technology is almost useless

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 training method and device, speech recognition method and device, electronic equipment and storage medium
  • Speech training method and device, speech recognition method and device, electronic equipment and storage medium
  • Speech training method and device, speech recognition method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of means and devices consistent with some aspects of the present disclosure, as recited in the appended claims.

[0072] figure 1 A schematic flowchart of a voice training method shown in an embodiment of the present disclosure, as shown in figure 1 As shown, the voice training method of the embodiment of the present disclosure includes the following steps:

[0073] S11. Acquire a first data set and a first speech recognition model.

[0074] In the embodiment of the present disclosure, the first speech recogni...

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 relates to a voice training method and device, a voice recognition method and device, electronic equipment and a storage medium. The voice training method comprises the following steps: acquiring a first data set and a first voice recognition model; the first speech recognition model is a model trained through a neural network based on a second data set; the first data set comprises a plurality of first data sample combinations, and each first data sample combination comprises the first type of voice data and a label corresponding to the first type of voice data; the second data set comprises a plurality of second data sample combinations, and each second data sample combination comprises a second type of voice data and a label corresponding to the second type of voice data; the first data set is adopted to train a second voice recognition model until the recognition rate of the second voice recognition model meets a preset condition, and the trained second voice recognition model is obtained; wherein the second recognition model comprises a full connection layer and a first speech recognition model.

Description

technical field [0001] The present disclosure relates to speech recognition technology, and in particular, to a speech training method and device, a speech recognition method and device, an electronic device, and a storage medium. Background technique [0002] The current speech recognition technology is relatively mature. For normal speech input, the recognition accuracy rate is relatively high and it has been commercialized. However, for people with language impairments such as cerebral palsy, slurred speech, etc., the accuracy of recognizing the speech of such people is extremely low, and the current speech recognition technology can hardly be used. For this part of the staff, whether they are going out or at home, they have great communication needs, and the demand for voice recognition is even stronger. SUMMARY OF THE INVENTION [0003] The present disclosure provides a voice training method and device, a voice recognition method and device, an electronic device, and...

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): G10L15/06G10L15/16G10L15/183G10L15/26
CPCG10L15/063G10L15/16G10L15/183G10L15/26
Inventor 王育军
Owner BEIJING XIAOMI PINECONE ELECTRONICS CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products