Method and device for audio information retrieval
An audio information and audio technology, applied in the field of data processing, can solve the problems of low efficiency and long time spent in audio information retrieval, and achieve the effect of ensuring normal Internet experience
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] Through the analysis of the uploaded audio information, it is found that the data in each malicious audio information has a large number of repetitions with each other. For example, the user may upload a single audio information containing malicious information multiple times, or upload the audio information after simple editing, etc. We can call such audio information with a large amount of repeated content as homologous information. For example, for a piece of audio information A, the user can insert some other audio data into its audio information, and then recompress to obtain audio information B, then audio information B is the same source information of audio information A. That is to say, when the audio information A has been determined to contain malicious information, the audio information A can be stored as a sample audio in the audio feature library, and the homologous information with the sample audio is determined to contain malicious information. The audio...
Embodiment 2
[0103] refer to image 3 , image 3 A structural diagram of an audio information retrieval device provided in this embodiment, the device may include:
[0104] The first acquiring module 301 is configured to acquire audio information to be processed;
[0105] The second acquiring module 302 is configured to acquire the audio data of the audio information to be processed;
[0106] An extraction module 303, configured to extract a feature group of the audio data, the feature group including no less than one feature;
[0107] The extraction module may include:
[0108] A framing submodule, configured to divide the audio data into frames to obtain frame data;
[0109] The transformation sub-module is used to perform short-time Fourier transform on the frame data to obtain transformed frame data;
[0110] The frequency division sub-module is used to divide the converted frame data into frequency to obtain a spectrum diagram;
[0111] The extraction submodule is used to extract ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com