A method, device and system for processing intelligent voice interaction interruption

Abstract

This application provides an intelligent voice interaction interruption processing method, device and system. When the user needs to interrupt the target voice that the robot is playing, the user sends the interruption voice to the robot. At this time, the robot responds to the interruption voice and determines the The first timestamp corresponding to the current voice being played. In order to ensure the integrity of the playback when the current voice stops playing, an interruptible timestamp will be set in the current voice in advance as the node that actually interrupts the playback of the voice. After the robot determines the first timestamp, it needs to determine the corresponding interruptible timestamp according to the first timestamp, that is, the second timestamp. In order to stop playing the voice in time, select the first interruptable timestamp after the first timestamp Timestamp as the second timestamp. In this way, by continuously playing the current voice until the second time stamp, not only can the playback integrity of the voice be ensured, but also the playback of the current voice can be stopped in a timely manner, so as to respond to other demands put forward by the user in a timely manner.

Description

technical field [0001] The present application relates to the technical field of natural language processing, and in particular to an intelligent voice interaction interruption processing method, device and system. Background technique [0002] Human-computer interaction (HCI), also known as human-machine interaction (HMI), refers to the interaction between the user and the system. The use of human-computer interaction can effectively reduce labor costs. For example, in the field of customer service, replacing human customer service with robots, and using robots to communicate with users through voice to solve some problems and needs of users can effectively reduce the number of workers. [0003] In order to improve the user's experience, it is necessary to make the playback mode of the robot's voice, such as voice content, tone of voice, speed of speech, and response to the user's voice, more close to the mode of human dialogue. Among them, the response to the user's voice,...

AI Technical Summary

Problems solved by technology

[0003] In order to improve the user's experience, it is necessary to make the playback mode of the robot's voice, such as voice content, tone of voice, speed of speech, and response to the user's voice, more close to the mode of human dialogue. Among them, the response to the user's voice, It is difficult for a robot to imitate a human conversation. For example, when a user does not want to continue listening to the robot replying to the current question, he will send a voice to the robot to interrupt the robot from playing the current voice. Usually, it is difficult for the robot to stop when it receives the user's voice signal. Play the interrupt point of the current voice. In some cases, the robot will choose to stop playing the current voice immediately or randomly, and this interruption method will cause the pronunciation or semantics of the voice that has been played to be incomplete, which does not conform to the way of human dialogue. It makes the user feel very blunt and the experience is poor; in some cases, in order to improve the integrity of the voice that has already been played, the robot will choose to extend the voice playback time, but this interruption method will make the current voice stop untimely , making users wait too long and reducing the experience

Images