Voice control method, voice control system, vehicle, server and storage medium

Abstract

The invention discloses a voice control method, a voice control system, a vehicle, a server and a storage medium. The voice control method includes: processing a received voice request to generate a current streaming text; obtaining a prediction result according to the current streaming text, and the prediction result includes a parameter predicting whether the next character of the current streaming text is a terminator; according to the current The traffic ratio corresponding to the streaming text, and the current parameter threshold is obtained. The traffic ratio is related to the request volume for natural language understanding of the streaming text; when the prediction result meets the preset judgment stop condition, the natural language understanding of the current streaming text is performed ; When the prediction result does not meet the preset judgment stop condition, the current streaming text is discarded. The above voice control method, by setting different preset judgment and stop conditions according to different situations, can effectively reduce the flow of flow text for natural language understanding, reduce the cost of flow, and can adjust different constraints on flow according to different situations.

Description

technical field [0001] The invention relates to the field of voice technology, in particular to a voice control method, a voice control system, a vehicle, a server and a storage medium. Background technique [0002] In the streaming voice interaction system, the voice is divided into uninterrupted small pieces, and in the process of streaming audio, the text conversion is also carried out synchronously. The natural language understanding module will receive multiple streaming voice-converted texts before the VAD tail frame is truncated, which will cause the traffic of the natural language understanding module to increase sharply. [0003] In the vehicle environment, traffic is also used in many links such as automatic driving and human-vehicle interaction. The increase in traffic may not only affect the realization of other functions that require traffic, but also cause an increase in hardware costs and a decrease in software processing speed. Therefore, in the streaming vo...

AI Technical Summary

Problems solved by technology

The natural language understanding module will receive multiple streaming voice-converted texts before the VAD tail frame is truncated, which will cause the traffic of the natural language understanding module to increase sharply

[0003] In the vehicle environment, traffic is also used in many links such as automatic driving and human-vehicle interaction. The increase in traffic may not only affect the realization of other functions that require traffic, but also cause an increase in hardware costs and a decrease in software processing speed.

Images