Method and system for operating presentations

Abstract

An embodiment of the present invention provides a presentation operation method. The method includes: receiving voice data from a speaker during the process of playing a presentation; sequentially determining each voice data segment according to a preset sentence segmentation strategy; inputting each voice data segment into a voice recognition engine in sequence, and judging each voice data Whether the segment hits the wake-up word of the control instruction; when there is a first voice data segment that does not hit the wake-up word of the control command, the first voice data segment is recognized word by word, and displayed word by word on the playback page of the presentation; When there is a second voice data segment that hits the wake word of the control instruction, the control instruction is executed to control the presentation. The embodiment of the present invention also provides an operating system for presentations. The embodiment of the present invention operates the presentation by using the instruction content generated by the voice, which completely liberates the hands of the presenter, and at the same time displays the words of the speech as subtitles to improve the effect of the speech.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a presentation operation method and system. Background technique [0002] With the development of multimedia technology, presentations have become a standard configuration for presentations due to their powerful functions, and are widely used in various scenarios such as press conferences, classrooms, and academic exchanges. A vivid speech can not only accurately and efficiently convey the information that the speaker wants to express, and leave a deep impression on the audience, but also has an important impact on subsequent product promotion and academic exchanges. [0003] By using presentation software, you can create a presentation that integrates multimedia elements such as text, graphics, images, sounds, and video clips, and organize the information to be expressed in a set of pictures with both pictures and texts, which can introduce the company's products visually...

AI Technical Summary

Problems solved by technology

[0008] In order to at least solve the problem in the prior art when the speaker is separated from the multimedia device, the speaker cannot directly control the presentation, the existing device is incomplete and cannot completely release the speaker's hands, and in a complex environment, the speech The content expressed by the speaker cannot be completely conveyed to the audience

Images