A method and device for audio recognition

An audio recognition and audio streaming technology, applied in the audio field, can solve the problems of interrupting users watching videos, failure to retrieve, and low accuracy, and achieve the effects of improving retrieval efficiency and retrieval success rate, speeding up retrieval speed, and fast recognition speed

Active Publication Date: 2018-10-30
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The first and second methods above search based on keywords, but the operation is cumbersome and requires the user to continuously view and filter the search results. If you encounter niche music, you may not be able to retrieve it
[0008] Although the above-mentioned methods 3 and 4 can solve the problems of cumbersome retrieval and inaccessible retrieval in methods 1 and 2, users need to manually record and then retrieve, which is cumbersome to operate
And the 3rd and 4th methods are carried out by recording, if the recording environment is very noisy, the accuracy rate of retrieval through the recording is very low
In addition, the third and fourth methods are very inconvenient to apply in many occasions. For example, if a user wants to record a voice while watching a video on a mobile terminal, he must switch to the recording software to complete the recording, and then complete the retrieval, so it will be interrupted. The user's viewing process of the video

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
  • A method and device for audio recognition
  • A method and device for audio recognition
  • A method and device for audio recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] refer to figure 1 , which shows a schematic flow chart of an audio recognition method, which may specifically include:

[0081] Step 110, intercepting the audio stream of the first time length from the source data of the video file;

[0082] It should be noted that, in the embodiment of the present invention, the video file may be obtained from various video websites. Specifically, all video files on the network are crawled in advance, and for each video file, an audio stream of a first time length is intercepted from the source data of the video file, and audio information identification is performed on the audio stream.

[0083] In another embodiment of the present invention, the video file may also be a video file currently being played by the user. Specifically, when the user is watching a video file and is very interested in the background music of the currently playing video, the operation of identifying the background music can be triggered; An audio stream of...

Embodiment 2

[0256] refer to figure 2 , which shows a schematic flow chart of an audio recognition method, which may specifically include:

[0257] Step 210, judge whether to receive the recognition instruction of background music triggered by the user; If receive the recognition instruction of background music triggered by the user, then enter step 220; If not receive the recognition instruction of background music triggered by the user instruction, then go to step 230.

[0258] In the embodiment of the present invention, the user clicks on a video file through the video playback terminal on the client terminal, and when the user is interested in a certain background music during video playback, an instruction to identify the background music can be triggered. The video playback terminal receives an instruction to identify background music triggered by a user.

[0259] In practical applications, an audio recognition interface can be provided for the user in a video playback terminal, w...

Embodiment 3

[0291] It is an audio recognition method in the application environment where the video player of the mobile terminal is used.

[0292] refer to image 3 , showing a schematic flowchart of an audio recognition method in a video player, which may specifically include:

[0293] Step 310, the video player intercepts the audio stream of the first time length from the source data of the video file;

[0294] Step 320, the video player retrieves corresponding audio information according to the audio stream of the first time length, and displays it to the user.

[0295] Preferably, step 305 may also be included before step 310:

[0296] Step 305, in the process of playing the video, receiving an instruction to identify the background music;

[0297] In practical applications, the user's recognition instruction for background music is received through the audio recognition interface of the video player.

[0298] In the embodiment of the present invention, the audio recognition inte...

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 application relates to the field of audio technology, provided in embodiments are a method and device for audio identification. The method comprises: capturing an audio stream of a first length from source data of a video file; retrieving corresponding audio information according to the audio stream of a first length, and displaying the same to a user; the corresponding audio information retrieved according to the audio stream of a first length comprising: dividing the audio stream into at least two sub-audio streams according to a preset rule; sequentially retrieving the sub-audio streams obtained from the dividing, so as to obtain the audio information. The embodiments of the present application are able to extract an audio stream directly from a video source data which is currently being played so as to be retrieved, which requires no extra recording operations and is unaffected by noisy environments. The present application has simple operations and is highly accurate; the retrieving process thereof would not affect a user's normal viewing a video, while improving retrieving efficiency and success rate.

Description

technical field [0001] The present application relates to the field of audio technology, in particular to an audio recognition method and device. Background technique [0002] Now more and more users watch videos through the Internet, such as watching online videos through a browser or video player on a PC, or watching online videos through a browser or a video player on a mobile terminal. However, the user may encounter the following situation in the process of watching the video: there is a nice background music or episode in the video playback, and the user wants to know the detailed information of the background music. But in the prior art, if the user needs to know the detailed information of the background music, it may have the following acquisition means: [0003] 1. The user searches in the search engine according to the video name. [0004] 2. The user memorizes the lyrics of the background music, inputs the lyrics into the search engine, and inquires about the i...

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): H04N21/439G10L25/54
CPCG06F16/00
Inventor 姚光超
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT 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