VAD tail point detection method and device, server and computer readable medium

Abstract

The invention provides a VAD tail point detection method and intelligent equipment. The method comprises the following steps: determining a probability pa that a speech packet contains a VAD tail point, decoding the speech packet, determining the probability pn of semantic integrity of a text instruction corresponding to the speech packet, and determining whether the speech packet contains the VADtail point or not according to pa, pn and a preset threshold value, and combining acoustic VAD detection and semantic VAD detection to realize VAD tail point detection. The VAD tail point detection is more accurate, false detection caused by speech pause can be avoided, the problem of slow response caused by overlong VAD tail point in the speech packet is solved, and the user experience in the speech man-machine interaction process is improved. The invention further provides a server and a computer readable medium.

Description

technical field [0001] The present disclosure relates to the technical field of speech recognition, and in particular to a VAD tail point detection method, device, server and computer readable medium. Background technique [0002] Voice human-computer interaction refers to the interaction with smart devices using voice as the information carrier. In recent years, with the development of voice recognition technology and the popularization of smart devices, voice human-computer interaction has become an important way of human-computer interaction in such as smart speakers, home appliances and vehicle-mounted equipment. [0003] In the process of voice human-computer interaction, the speech speed and pause of the user's voice commands in different scenarios are random, so the following two bad interaction experiences may occur: one case is that the user speaks at a faster speed For voice commands, in some special scenarios, the smart device may wait for a period of time before...

AI Technical Summary

Problems solved by technology

[0003] In the process of voice human-computer interaction, the speech speed and pause of the user's voice commands in different scenarios are random, so the following two bad interaction experiences may occur: one case is that the user speaks at a faster speed Voice commands, in some special scenarios, the smart device may wait for a period of time before responding, giving the user the feeling that the smart device is "sluggish"

Another situation is that the user speaks slowly or pauses in the voice command. In this case, voice truncation may occur, which will directly affect the subsequent voice recognition results.

Images