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

Speech error correction method, device, equipment and storage medium

An error correction method and voice technology, which is applied in the computer field, can solve problems such as the lack of differentiated voice error correction methods in the field of voice error correction, and achieve the effect of accurate response and improved accuracy

Active Publication Date: 2021-12-17
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing voice error correction methods are usually aimed at some error correction methods that are generally applicable to the public, and there is still a lack of differentiated voice error correction methods for specific users in the field of voice error correction

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 error correction method, device, equipment and storage medium
  • Speech error correction method, device, equipment and storage medium
  • Speech error correction method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a flow chart of the voice error correction method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where, in a voice interaction scenario, for a specific user, combined with the user's own personalized information, the user's voice is corrected. The method can be executed by a speech error correction device, which can be implemented in the form of software and / or hardware, and can be integrated on any device with computing capability, including but not limited to a server.

[0026] like figure 1 As shown, the voice error correction method provided in this embodiment may include:

[0027] S110. Determine at least one language type to which the current query voice belongs according to the user's current query voice and user description information, where the language type includes Mandarin and at least one dialect.

[0028] In the voice interaction scenario, the user's query voice carries the user's query r...

Embodiment 2

[0047] figure 2 It is a flow chart of the speech error correction method provided by Embodiment 2 of the present invention. This embodiment further optimizes and expands on the basis of the foregoing embodiments. like figure 2 As shown, the method may include:

[0048] S210. Determine at least one language type to which the current query voice belongs according to the user's current query voice and user description information, where the language type includes Mandarin and at least one dialect.

[0049] Exemplarily, according to the user's current query voice and user description information, a pre-trained language type analysis model may be used to determine at least one language type to which the current query voice belongs. The language type analysis model is used to predict the language type of the user's query speech. The training process of the language type analysis model includes: taking the query voice and user description information of multiple sample users (re...

Embodiment 3

[0067] image 3 It is a schematic structural diagram of the speech error correction device provided by Embodiment 3 of the present invention. This embodiment is applicable to the case of correcting a user's speech for a specific user in combination with the user's own personalized information in a speech interaction scenario. The voice error correction device provided in this embodiment can be realized by software and / or hardware, and can be integrated on any device with computing capability, including but not limited to a server.

[0068] like image 3 As shown, the speech error correction device provided in this embodiment includes a language type determination module 310, a speech error correction model determination module 320 and a speech error correction module 330, wherein:

[0069] A language type determination module 310, configured to determine at least one language type to which the current query voice belongs according to the user's current query voice and user de...

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 embodiment of the present invention discloses a voice error correction method, device, device, and storage medium, wherein the method includes: determining at least one language type to which the current query voice belongs according to the user's current query voice and user description information, wherein , the language type includes Mandarin and at least one dialect; determine the speech error correction model corresponding to each language type; use the various speech error correction models determined to perform speech analysis on the current query speech, and perform speech error correction based on the speech analysis results . The embodiment of the present invention can realize personalized speech error correction for different users, and improve the accuracy of speech error correction.

Description

technical field [0001] The embodiment of the present invention relates to the field of computer technology, and in particular to a voice error correction method, device, equipment and storage medium. Background technique [0002] In the voice-based human-computer interaction scenario, accurate recognition of user voice is an important link to ensure the smooth progress of the interaction process. With the continuous development of voice interaction technology, in the process of recognizing the user's voice, it can also automatically correct the error of the user's voice, accurately predict the user's semantics, and ensure the user's interactive experience. [0003] However, the existing voice error correction methods are usually aimed at some error correction methods that are generally applicable to the public, and there is still a lack of differentiated voice error correction methods for specific users in the field of voice error correction. Contents of the invention [...

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): G10L15/00G10L15/06G10L15/16G10L15/18G10L25/51H04W4/021
CPCG10L15/005G10L15/063G10L15/1815G10L15/16G10L25/51H04W4/021G10L15/22G10L2015/227G10L15/187
Inventor 时迎超黄际洲
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD