Audio data processing method based on voice recognition

A technology of audio data and speech recognition, applied in speech recognition, speech analysis, subscriber special services, etc., can solve problems such as heavy workload, improve accuracy and reliability, improve reliability and accuracy, and prevent data processing bad effect

Inactive Publication Date: 2020-07-10
徐琼琼
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for processing audio data based on speech recognition, which is used to solve the problem that the manual analysis and processing of audio data will bring a lot of work

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
  • Audio data processing method based on voice recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] This embodiment provides an audio data processing method based on speech recognition. The execution subject of the audio data processing method may be a smart mobile terminal, a notebook computer or a desktop computer, or a server. This embodiment does not include the execution subject Do limited. In this embodiment, the audio data processing method is realized by executing an application program in a computer. The processing object of the audio data processing method is audio data, if the audio data is audio data collected in real time, the computer is also equipped with a microphone device to collect audio data; if the audio data is an external device, such as background monitoring center download to the computer, the computer does not need to be equipped with a microphone device.

[0035] Such as figure 1 Shown, this audio data processing method comprises the steps:

[0036] Get audio data:

[0037] The audio data of the object to be inspected is obtained through...

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 an audio data processing method based on voice recognition. Obtained audio data are divided into at least two sub-audio segments and two processing modes are carried out on the sub-audio segments. According to the first processing mode, the sub-audio segments are converted into a voice oscillogram; whether abnormal emotion exists in the audio data or not is determined according to the amplitude fluctuation condition of the voice oscillogram and a preset emotion abnormal amplitude fluctuation threshold value; and the emotion abnormality judgment result is stored into apreset audio data processing result database; and according to the second processing mode, sub-audio-band voices are recognized to obtain audio text data, audio keywords in the audio data are obtainedaccording to a preset audio keyword database, the audio keywords are stored in an audio data processing result database, and finally, the audio data processing result database is output. According tothe audio data processing method, reliable processing of the audio data is realized, the workload of the quality inspection personnel is reduced, subjective judgment influence caused by human factorsis avoided, and the accuracy is relatively high.

Description

technical field [0001] The invention relates to an audio data processing method based on speech recognition. Background technique [0002] In many organizations, with the development of business, it is necessary to equip professional customer service personnel to provide services to customers to meet the needs of business development. Customer service personnel need to connect and handle many calls every day. In order to monitor the service quality of customer service personnel in real time, special quality inspection personnel are usually required to analyze and process the real-time audio data of customer service personnel, such as obtaining relevant keywords in the audio data, Subsequent scoring is performed according to the keywords obtained from the processing, and the emotional situation of the customer service staff when speaking the audio data is obtained according to the manual analysis of the audio data, and subsequent scoring is performed according to the emotiona...

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): G10L25/63G10L25/18G10L15/22H04M3/51
CPCG10L15/22G10L25/18G10L25/63H04M3/5175
Inventor 徐琼琼陈海清
Owner 徐琼琼
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap