Check patentability & draft patents in minutes with Patsnap Eureka AI!

Speech recognition result correction method, device, equipment and storage medium

A speech recognition and text recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem that the accuracy of acoustic model recognition needs to be further improved, and achieve the effect of improving the accuracy.

Active Publication Date: 2020-11-20
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the recognition accuracy of the acoustic model needs to be further improved

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 result correction method, device, equipment and storage medium
  • Speech recognition result correction method, device, equipment and storage medium
  • Speech recognition result correction method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flow chart of a speech recognition result correcting method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of correcting speech recognition results, and the method can be executed by the speech recognition result correcting device provided in the embodiment of the present invention , the device may be implemented in software and / or hardware, and the device may be integrated in the terminal device or in an application end of the terminal device. Wherein, the terminal device may be, but not limited to, a mobile terminal (tablet computer or smart phone).

[0031] Wherein, the application end may be a plug-in of a certain client embedded in the terminal device, or a plug-in of the operating system of the terminal device, and the speech recognition result embedded in the terminal device may correct the operation of the client or the terminal device. The voice recognition result correction application progra...

Embodiment 2

[0044] Figure 2A It is a flow chart of a method for correcting speech recognition results provided by Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, the step is to further use the neural machine translation NMT model to identify and correct the initial text information, and the final text recognition result is optimized as follows: the initial text information contains The text is segmented to obtain at least one word; the word is encoded into a dense vector by the encoder in the NMT model, and the dense vector is decoded by the decoder in the NMT model to obtain the final text recognition result.

[0045] Correspondingly, such as Figure 2A As shown, the method of this embodiment specifically includes:

[0046] S201. Perform speech recognition on the acquired speech data to obtain initial text information.

[0047] S202. Segment the text included in the initial text information to ob...

Embodiment 3

[0055] Figure 3A It is a flow chart of a method for correcting speech recognition results provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, further steps are to encode words into dense vectors through the encoder in the NMT model, and decode the dense vectors through the decoder in the NMT model to obtain The final text recognition result is optimized as follows: convert at least one word into a source hidden state vector through the encoder in the NMT model; input the source hidden state vector into the decoder in the NMT model, and output the target hidden state vector through the decoder in the NMT model State vector; determine the hidden state vector of the attention mechanism according to the target hidden state vector and the source hidden state vector; obtain the final text recognition result according to the hidden state vector of the attention mechanism.

[0056] Corre...

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

A method and apparatus for correcting a speech recognition result, a device and a computer-readable storage medium are provided. The method includes performing speech recognition on acquired speech data to obtain initial text information; and recognizing and correcting the initial text information by a neural machine translation NMT model to obtain a final text recognition result.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of speech recognition, and in particular, to a method, device, device, and storage medium for correcting speech recognition results. Background technique [0002] With the rapid improvement of computer processing capabilities, speech recognition technology has been developed rapidly. Speech recognition technology is a technology that converts speech signals into corresponding text or commands through the process of recognition and analysis. The application of speech recognition technology is changing the production and life style of human beings day by day, and is widely used in fields such as speech input system, speech control system and intelligent dialogue query system. [0003] As the most natural way of interaction, voice interaction is increasingly popularized, and the requirements for the accuracy of voice recognition are getting higher and higher. At present, the speech recogn...

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): G10L15/22G10L15/26
CPCG10L15/22G10L15/26G10L15/16G10L15/04G10L15/063
Inventor 黄俊李先刚
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com