Speech optimization method and device applied to intelligent robot

Abstract

The invention discloses a voice optimization method and a voice optimization device applied to an intelligent robot. The voice optimization method comprises the steps of: acquiring multi-modal input data of a user; generating text information in response to the multi-modal input data; performing text analysis on the text information when determining that a set triggering rule is satisfied, and querying a corresponding media file and response information according to an analysis result; and outputting the media file and TTS voice generated by a TTS system in response to the response information according to a set rule. By outputting the media file and the TTS voice in a combined manner, the voice output of the robot has more features of a human language, the rhythm is good, the user feels comfortable, the capability of the robot is enhanced, and the interaction demand of users is satisfied.

Description

technical field

[0001] The invention relates to the field of intelligent robots, in particular to a voice optimization method and device applied to intelligent robots. Background technique

[0002] With the gradual popularization of intelligent robot products, more intelligent robots have entered the family, becoming children's playmates and adults' housekeepers.

[0003] Existing intelligent robots have been able to answer users' questions or conduct simple chats with users through verbal communication. However, due to technical limitations, the voices of robots when communicating with users are still mainly machine voices. It is relatively tough and without emotion, so the existing human-computer interaction process will bring bad experience to users.

[0004] Therefore, there is an urgent need to provide a solution that can optimize the sound experience, make the user interacting with the robot feel comfortable, improve the interaction ability of the intelligent robot, a...

Images