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

A system and method for automatically scoring Internet audio data quality

An audio data, Internet technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as low accuracy and mismatch of Internet speech data

Active Publication Date: 2020-05-15
深圳撒哈拉数据科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The main purpose of the present invention is to provide a system and method for automatically scoring the quality of Internet audio data to solve the problems of mismatching and low accuracy in evaluating Internet audio data in the prior art

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
  • A system and method for automatically scoring Internet audio data quality
  • A system and method for automatically scoring Internet audio data quality
  • A system and method for automatically scoring Internet audio data quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0089] Such as figure 1 As shown, the present invention proposes a kind of Internet audio data quality automatic scoring system, comprising:

[0090] Feature extraction module 10, for extracting a plurality of sound features of voice data;

[0091] The basic scoring system module 20 is used to obtain a plurality of first score values ​​of the first voice data by presetting a set of first voice data, and use the feature extraction module to perform feature extraction and pre-whitening of the first voice data, Obtaining a plurality of first pre-whitening sound features of the first voice data, fitting the first sound features and the data of the first scoring value, and establishing a basic scoring system;

[0092] The system update module 30 is used to obtain a group of second voice data, extract the features of the ...

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 present invention provides an audio data quality automatic scoring system and method. The system comprises a feature extraction module, a basic scoring system module and a system updating module. The system updating module is configured to obtain one group of second speech data and extract the features of the second speech data, the basic scoring system module is configured to score the second speech data and obtain a second scoring value, according to the scoring value, the second speed data is classified to obtain three speed data of a large value, an intermediate value and a small value, the two data of the large value and the small data are employed to perform system training and perform updating of the basic scoring system. Aiming at the new requirement of the intelligent voice interaction, a self-adaption correction quality scoring model capable of reflecting the hearing feature of the noise interference degree and assessing the improvement degree of the speed interaction accuracy in real time is designed to realize the purpose of accurately selecting high-quality internet data to improve the speech interaction accuracy.

Description

technical field [0001] The invention relates to the field of voice technology, in particular to an automatic scoring system and method for Internet audio data quality. Background technique [0002] In recent years, with the vigorous development of Internet technology and intelligent hardware, voice intelligent interactive technologies such as voice recognition, voiceprint recognition, and sound source detection have begun to move from laboratories to users. These speech signal processing techniques are usually based on a database covering basic applications, and are mathematically modeled through related machine learning techniques. The more adequate the database, the higher the accuracy of the mathematical model. The massive voice data on the Internet is more real and sufficient than the manually collected database. Making full use of these massive data will significantly improve the accuracy of existing voice signal processing technologies. However, due to the randomness...

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): G10L15/02G10L15/06G10L15/08G10L25/18G10L25/21G10L25/60
CPCG10L15/02G10L15/063G10L15/08G10L25/18G10L25/21G10L25/60
Inventor 蔡钢林
Owner 深圳撒哈拉数据科技有限公司