Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Voice recognition method and system based on deep learning

A technology of speech recognition and speech, which is applied in speech recognition, speech analysis, instruments, etc., can solve the problems of long waiting time for an answer, and spend a lot of time and energy for electric customers, so as to reduce the waiting time for answering and reduce the workload Effect

Inactive Publication Date: 2019-01-04
YUNNAN POWER GRID +1
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem in the prior art that manual customer service requires a lot of time and effort to listen to voice query requests sent by all users, and the customer waits for a long time to answer when using the phone, this application discloses a method based on the following various embodiments. Speech recognition method and system based on deep learning

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
  • Voice recognition method and system based on deep learning
  • Voice recognition method and system based on deep learning
  • Voice recognition method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to solve the problem in the prior art that manual customer service requires a lot of time and effort to listen to voice query requests sent by all users, and the customer waits for a long time to answer when using the phone, this application discloses a method based on the following various embodiments. Speech recognition method and system based on deep learning.

[0060] The first embodiment of the present application discloses a speech recognition method based on deep learning, see figure 1 As shown in the schematic diagram of the workflow, the method includes:

[0061] In step S11, a training data set is obtained, and the training data set includes: a training voice data set, voice tags, and dialogue text information.

[0062] Wherein, the training voice data set is a pre-prepared power business voice data set, including the recording data of power customer service. Professional vocabulary and questions such as compensation, manual refund, meter reading ac...

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 application discloses a voice recognition method and system based on deep learning. The method includes the following steps: acquiring a training data set, wherein the training data set includes atraining voice data set, a voice label and dialogue text information; training the training data set through a training process, and establishing an acoustic model and a language model; acquiring voice query request data; carrying out voice recognition on the voice query request data according to the acoustic model, the language model and a preset dictionary; and finally, outputting a voice recognition text result of the voice query request data. Through the voice recognition method based on deep learning provided by the application, voice consulting content input by customers can be accurately identified, the workload of the manual customer service staff needing to listen to all the consulting requests is reduced, and the time for customers to wait for response is reduced.

Description

technical field [0001] The present application relates to the technical field of speech recognition, in particular to a method and system for speech recognition based on deep learning. Background technique [0002] With the continuous deepening of the reform of the power system, in order to obtain electricity-related information in real time for customers using electricity, power companies need to provide customers with information about power inquiries, power outage announcements, outlet inquiries, power consumption knowledge, and power supply business management information through various platforms. and other consulting services. In addition, in order to facilitate internal employees to obtain enterprise information, power companies also need to provide internal employees with various query services such as internal message notification, business knowledge query, business interface push, and operation and maintenance service table query. [0003] However, the inventor fo...

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): G10L15/06
CPCG10L15/063G10L2015/0633
Inventor 游绍华赵涛赵毅涛张羿浦朔吴迟林陈姣
Owner YUNNAN POWER GRID
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com