Audio abstract text creation method based on speech recognition and creation device thereof

A technology of speech recognition and audio files, applied in speech recognition, speech analysis, instruments, etc.

Active Publication Date: 2018-07-20
HAIER YOUJIA INTELLIGENT TECH (BEIJING) CO LTD
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problems described above, and provides a method and device for enabling users to conveniently and quickly create audio summary texts for audio files such as books

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
  • Audio abstract text creation method based on speech recognition and creation device thereof
  • Audio abstract text creation method based on speech recognition and creation device thereof
  • Audio abstract text creation method based on speech recognition and creation device thereof

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0057]The first embodiment of the present invention is described for the case of creating an audio summary once, please refer to figure 2 . The so-called one-time creation of an audio summary means that the summary creation command is only received once during the playback of an audio file.

[0058] First, there is a shortcut for the user to issue a create summary command for the audio file being played. The shortcut here includes using a shortcut key or a combination of multiple shortcut keys. The command to create a summary may be a command issued by a hardware component of the device, for example, a signal issued when the volume down key and a power key are pressed simultaneously on a mobile phone, or a signal issued when a certain key is pressed and held. Another example is the touch screen signal received by the playback software when playing audio, such as the signal of double-clicking the screen, the signal of drawing a preset graphic on the screen, and so on. Creat...

no. 2 example

[0064] The second embodiment of the present invention is described for the situation of creating audio summaries multiple times, please refer to figure 2 . The multiple creation of audio abstracts in this embodiment is relative to the single creation of audio abstracts in the first embodiment. Because in the process of actually listening to the audio file, the audience may not only be interested in a piece of content, but hear different exciting parts continuously. At this time, it is necessary to use the method of creating audio summaries multiple times to meet the audience's demand for simultaneous creation of summaries for multiple pieces of content. The specific content includes the following steps:

[0065] First, the first creation summary command is still received when playing an audio file;

[0066] Secondly, determine the playback position of the audio file when receiving the summary command for the first time; determine the position information of the target audi...

no. 3 example

[0080] The present invention also provides a device for creating audio summary text based on speech recognition, such as Figure 4 ,include:

[0081] Command receiving module: used to receive the creation summary command when playing the audio file;

[0082] Playing position determination module: used to determine the playing position of the audio file when receiving the creation summary command;

[0083] Audio segment position determination module: connected to the playback position determination module, used to determine the position information of the target audio segment according to the playback position;

[0084] Obtaining module: used to obtain the audio content in the target audio segment;

[0085] Recognition module: used to recognize audio content to obtain text information.

[0086] Wherein, the method for determining the location information of the target audio segment by the audio segment position determination module includes any one of the following:

[0087...

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 present invention provides an audio abstract text creation method based on speech recognition and a creation device thereof. The creation method comprises the following steps of (S1) receiving anabstract creation command when an audio file is played, (S2) determining a playing position of the audio file when the abstract creation command is received, (S3) determining position information of atarget audio segment according to the playing position, (S4) acquiring audio content in the target audio segment, and (S5) identifying the audio content to obtain text information. According to the method and the device, an audio abstract can be conveniently and quickly created without the further use of other editing software, and the audio abstract is converted into a text abstract for storage.On one hand, a reader can conveniently and quickly understand the summary of a new book that has not been read by listening, on the other hand, the reader can conveniently save concerned audio clipsin real time, so the reader can accurately recall the content of the book that has been read by listening in the future, and so the targeted selection of listening or not by the reader is facilitated.

Description

technical field [0001] The present invention relates to the technical field of voice information processing, in particular to a method and device capable of creating abstracts for real-time played voice files. Background technique [0002] With the rapid development of smart phones, people's reading methods have also undergone drastic changes. With the emergence of various "listening to books" software, more and more people have switched from traditional reading to listening to books. The benefits of listening to books are numerous, such as protecting eyesight, saving resources, being free from external influences anytime, anywhere, and so on. However, for current audiobook players, there are also some disadvantages. For example, when a user listens to a brand new book, if he wants to determine whether the audio book is suitable for him in a short period of time, he needs to browse the book quickly. And because the existing player can only realize the order complete playin...

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 Applications(China)
IPC IPC(8): G10L15/22G10L15/26H04N21/854H04N21/439
CPCG10L15/22G10L15/26H04N21/439H04N21/854
Inventor 王守峰李晓琳
Owner HAIER YOUJIA INTELLIGENT TECH (BEIJING) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap