Unlock instant, AI-driven research and patent intelligence for your innovation.

Method, device, equipment and readable storage medium for ear speech restoration

A recovery method, ear-to-ear technology, applied in speech analysis, speech recognition, neural learning methods, etc., can solve problems such as the inability of machines to accurately identify user content

Active Publication Date: 2021-05-04
IFLYTEK CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in meetings or occasions involving privacy, normal use of voice input will bring some inconvenience, and many users will choose to whisper, which introduces the problem that the machine cannot accurately recognize what the user said

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
  • Method, device, equipment and readable storage medium for ear speech restoration
  • Method, device, equipment and readable storage medium for ear speech restoration
  • Method, device, equipment and readable storage medium for ear speech restoration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0095] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0096] Next, combine the figure 1 , introduce the ear speech restoration method of the present application, such as figure 1 As shown, the method includes:

[0097] Step S100, obtaining the acoustic features of the ear speech data corresponding to the ear speech data, and the preliminary recognition results corresponding to the ear speech data;

[0098] Specifically, in this step, the earphonetic acoustic features corresponding to the externally input earphonetic data may be direc...

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 discloses a method, device, equipment and readable storage medium for ear speech restoration, which is realized based on the ear speech restoration model. The ear speech restoration model uses the recognition results of the ear speech training data and the acoustic features of the ear speech training as samples in advance. , obtained by training with the normal voice acoustic features corresponding to the normal voice data parallel to the ear voice training data as sample labels. This application obtains the earphone acoustic features corresponding to the earphone data, and the preliminary recognition results corresponding to the earphone data, and then inputs the earphone acoustic features and preliminary recognition results into the preset earphone restoration model to obtain the output normal voice acoustics feature, and can restore ear speech accordingly.

Description

technical field [0001] The present application relates to the technical field of speech recognition, and more specifically, to an ear speech restoration method, device, equipment and readable storage medium. Background technique [0002] Speech recognition enables machines to automatically convert speech into corresponding text through machine learning methods, thus endowing machines with functions similar to human hearing, and is an important part of artificial intelligence. With the continuous breakthrough of artificial intelligence technology and the increasing popularity of various intelligent terminal devices, speech recognition, as an important link in human-computer interaction, is widely used in various intelligent terminals, and more and more users are accustomed to using voice input. [0003] The voice includes normal voice and ear voice, wherein the ear voice refers to the voice produced by the user when whispering, and the normal voice refers to the voice when th...

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): G10L15/02G10L15/06G10L15/25
CPCG10L15/02G10L15/063G10L15/25G10L15/16G10L15/32G06N3/08G06N3/044G06N3/045G06N3/049G10L15/22G10L25/03G10L25/30G10L2015/0635G10L2015/227
Inventor 潘嘉刘聪王海坤王智国胡国平
Owner IFLYTEK CO LTD