Smart voice interaction method and system

Abstract

The invention discloses a smart voice interaction method and system. The method includes receiving voice data; performing voice recognition on the voice data and acquiring a voice recognition result;performing recognition rejection judgment on the voice recognition result according to a pre-constructed recognition rejection judgment model based on a semantic layer and acquiring a model output result; determining whether the voice data is man-machine interaction voice data or not according to the model output result; if the voice data is man-machine interaction voice data, performing semanticunderstanding on the voice recognition result and generating an interaction result according to a semantic understanding result, wherein the interaction result includes a response text. By utilizing the method and system provided by the invention, influence on man-machine interaction by noise-containing voice data can be reduced and error response of the man-machine interaction system is reduced.

Description

technical field [0001] The invention relates to the fields of voice signal processing and human-computer interaction, in particular to an intelligent voice interaction method and system. Background technique [0002] In recent years, with the rapid development of artificial intelligence technology, technologies such as speech recognition, semantic understanding, and speech synthesis have also entered the practical level. People are increasingly eager to communicate with machines naturally and conveniently. From the traditional one-question-and-answer voice interaction system to the more popular multi-round question-and-answer voice interaction system, human-computer interaction is getting closer and closer to human-human interaction. The user experience has been greatly improved. However, due to the complex and changeable actual interactive environment, various noise voices are often input, causing false responses of the interactive system. In order to prevent this from ha...

AI Technical Summary

Problems solved by technology

[0003] However, since the interactive environment is often complex and changeable during actual voice interaction, the existing system cannot prevent the input of noise during the interaction process; during the voice interaction process, the voice data received by the machine often has noise, such as background noise , the machine's own broadcast sound, non-interactive voice (such as the voice of everyone talking), etc., will affect the interaction process, interfere with the interactive system, and cause the machine to respond incorrectly, especially the voice of everyone talking, which cannot be judged by the existing system Whether the current voice data that people talk to is human-computer interaction voice data, which largely causes the wrong response of the machine, increases the system load, and reduces the user experience.

Images