Method and system for speech quality perception evaluation based on speech semantic recognition technology

A technology for semantic recognition and speech quality, applied in the field of communication, can solve the problems such as the inability to restore the thinking paradigm of the human brain, and the poor repeatability of subjective evaluation methods, and achieve the effect of solving poor repeatability and precise positioning.

CN108877839AActive Publication Date: 2018-11-23NANJING HOWSO TECH
8 Cites 28 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2018-11-23

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method and system for speech quality perception evaluation based on the speech semantic recognition technology. According to a text of a sender after user speech conversion and a text of a receiver after user speech conversion, text similarity evaluation is carried out based on a text similarity fitting algorithm; network parameters and event information of communicationunit connection networks of the sender and the receiver are displayed in real time and are stored; a user speech perception evaluation model is established by using speech information according to a telecom psychology algorithm and speech perception evaluation is carried out on a user; and then user perception evaluation is formed by means of text similarity evaluation , network information and voice perception evaluation. With the method disclosed by the invention, problems of poor repeatability of the subjective evaluation method and the human brain thinking paradigm can not be restored by the objective issues can be solved; the method is close to the human brain thinking mode and the perception of the network conversation speech quality of the user; and on the basis of the time-positionmapping, a network issue can be located precisely by combining the network parameter information and events.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the communication field, in particular to voice services in the communication field, such as a network voice quality perception evaluation method related to 2G, Volte and network conversation voice (QQ and WeChat voice, etc.). Background technique

[0002] Voice services have always existed as the main business of operators from the analog network, GSM to today's 4G, and even in the future 5G era. When traditional services such as SMS and MMS have been eroded by OTT (over the top) service providers, voice services are The unique reliability and high QoS have been continuously used by everyone. However, users are not only satisfied with the acquisition of information when talking on mobile phones, but also pay more attention to the voice quality, whether it can restore the sound effect with high fidelity, and express human emotions. In this case, higher-definition voice is required to meet the demand. As an all-IP 4G v...

Examples

Embodiment Construction

[0169] Such as figure 1 As shown, the method for perceptual evaluation of speech quality based on speech semantic recognition technology specifically includes the following steps:

[0170] S1: Convert the voice and audio of the voice initiator into text information, and store the overall voice and audio information and the converted text information in the server for storage and simultaneously save the network parameters and event information of the voice initiator;

[0171] S2: Convert the voice and audio of the voice receiver into text information, and store the overall voice and audio information and the converted text information in the server for storage and at the same time save the network parameters and event information of the voice receiver;

[0172] S3: Evaluate the text similarity in step S1 and step S2 by using the method of text similarity, and display it in real time;

[0173] S4: Use the voice information to establish a user perception evaluation model through...