A method of audio stream replacement in video based on speech recognition

Abstract

The invention discloses a method for replacing an audio stream in a video based on speech recognition. The method is as follows: firstly, the front and rear endpoints of the people's speech in the audio are obtained by detecting the endpoints of the audio, then noise reduction is performed on the audio to extract feature values, and then speech recognition is performed through a sound model and a language model, and then according to the characteristics of the recognized words It is worth calculating the start and end time of the word, which is synthesized by calculating the speech characteristics of the speaker and the audio synthesized by the machine, so as to realize the audio stream replacement process in the video. The present invention can obtain the start time and end time of each word in the audio in the speech recognition result, obtain the start time and end time of each word in the audio in the recognition result, and make the audio stream replacement in the video more scientific through calculation It is accurate and can play a huge role in the field of speech recognition effect detection and video production.

Description

technical field [0001] The invention belongs to the technical field of speech recognition, and relates to a method for replacing an audio stream in a video based on speech recognition. Specifically, the start and end time of each word is calculated through audio analysis, so that when the audio stream part in the video changes, the newly generated audio can be seamlessly The method to replace the corresponding audio in the original video. Background technique [0002] In recent years, with the development of natural language processing technology, intelligent speech recognition and speech synthesis technology has gradually been put into production and life. However, the development of speech recognition technology is more common in the recognition of different languages, different recognition methods, and various methods to achieve better recognition effects, faster recognition speed and wider recognition range. For a video containing dialogues, speeches, etc., it is very d...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem of audio stream replacement, academia and industry have proposed many solutions, among which the technical solutions closer to the present invention are: In the invention patent with the patent publication number of CN 110019961A, the speech characteristics of the audio stream are obtained through speech recognition and speech synthesis method to modify the audio stream in the video stream, but in this patent, the synthesized audio is not modified, which may lead to heavy clipping traces of the video, out-of-sync sound and picture on a single word, etc.

Images