Voice interaction method and device, electronic equipment and storage medium

Abstract

The invention provides a voice interaction method and device, electronic equipment and a readable storage medium, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as voice technology and natural language processing. According to the specific implementation scheme, voice recognition is carried out on a request statement sent by a user, and at least one intermediate recognition result is obtained within first preset time after the request statement is received, wherein the end moment of the first preset time is earlier than the tail point moment of voice activity detection of the request statement; in response to the obtained first intermediate recognition result, whether the semantics of the at least one intermediate recognition result is complete or not is sequentially recognized according to the time sequence of the obtained at least one intermediate recognition result; and in response to a first intermediate recognition result with complete semantics recognized from the at least one intermediate recognition result, a first reply statement is determined for playing according to the first intermediate recognition result with complete semantics.

Description

technical field [0001] The present disclosure relates to the field of computer technology, specifically to the field of artificial intelligence technology such as voice technology and natural language processing, and in particular to a voice interaction method, device, electronic equipment, and storage medium. Background technique [0002] With the advancement of artificial intelligence technology, human-computer voice interaction (referred to as: voice interaction) has also been rapidly developed and widely used. For example, it can be widely used in smart TVs, smart speakers, virtual reality (virtual reality, VR) glasses and other smart equipment, and various voice assistant applications (APP). [0003] In traditional human-computer voice interaction, voice recognition and subsequent calls to dialogue services are performed serially, that is, voice recognition will be performed after the end of Voice Activity Detection (VAD) and based on the voice recognition The result c...

AI Technical Summary

Problems solved by technology

[0004] The inventors of the present disclosure have found through research that although the above-mentioned solution of streaming dialogue resources in advance can reduce the response time of voice interaction, in the process of streaming voice recognition, it is not known when the user will stop speaking. When the speech recognition result changes, the dialog service is called continuously, the corresponding result is obtained and cached, which leads to an increase in the request volume of the dialog service and a waste of a large amount of computing resources of the dialog service, especially for some resource services that need to be called for a fee In the case of Application Programming Interface (API), for example, when a dialogue service needs to call the interface of a weather service provider or an audio content provider to obtain a response resource, a pay-per-view is required, which will further increase the economic cost

Images