Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for generating audio and video subtitles

An audio-video and subtitle technology, applied in the field of audio-video subtitle generation methods and devices, can solve the problems of difficulty in finding an optimal path, difficult to achieve practical effects, and high hardware requirements, and achieve easy understanding, accurate synchronization, The effect of improving synchronization efficiency

Active Publication Date: 2019-10-18
IFLYTEK CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method directly uses a large segment of voice data and a large segment of text data for dynamic programming. Because the dynamic programming method needs to construct a search space according to the length of the text and voice, find the optimal path, and synchronize the voice data and text data according to the optimal path. ; If the length of text data and voice data is long, it is difficult to find the optimal path, the lower the search efficiency, and the search process has higher requirements on hardware, it is difficult to achieve practical results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for generating audio and video subtitles
  • Method and device for generating audio and video subtitles
  • Method and device for generating audio and video subtitles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0066] Such as figure 1 Shown, is a kind of flow chart of the audio-video subtitle generation method of the embodiment of the present invention, comprises the following steps:

[0067] Step 101, receiving voice data and text data of subtitles to be generated.

[0068] The voice data is generally a large segment of voice data with a long duration, and the text data is generally a large segment of text data that has not been segmented. For example, the voice data and text data of audio novels are generally longer.

[0069] Step 102: Segment the voice data according to the prosody of the speaker to obtain segments of voice data conforming to the habits of the speaker.

[0070] Segmenting the voice data according...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an audio and video subtitle generation method and apparatus. The method comprises the following steps: receiving voice data with subtitles to be generated and text data; according to the rhythm of speakers, segmenting the vice data to obtain each voice data segment according with habits of the speakers; according to the voice data segments, segmenting the text data to obtain text data segments corresponding to the voice data segments; and according to time information of each voice data segment, obtaining starting time and finishing time of the text data segments corresponding to the voice data segments. According to the invention, the text data can be displayed synchronously with the voice data in a simple and efficient mode, and the generated subtitles are more complete.

Description

technical field [0001] The invention relates to the technical field of voice processing, in particular to a method and device for generating audio and video subtitles. Background technique [0002] With the development of the mobile Internet and the popularization of smart terminals, people's needs for material culture are becoming more and more diverse. For example, people's reading habits are shifting from paper books to digital media, and audio and video related to books have appeared. People can Read by listening to the audio of an audiobook or watching a related video. The emergence of subtitles makes audio and video help people understand the content of audio and video in a more intuitive and reliable way. More and more users are used to audio and video files with subtitles. It is impossible to generate subtitles by using a segment of speech data and a large segment of text data. As a result, audio and video such as audio novels often do not have subtitles, and users ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/00G10L15/26
Inventor 周明江源王影胡国平胡郁刘庆峰
Owner IFLYTEK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products