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

Automatic audio summary generation method and device

An automatic generation, audio technology, applied in audio data retrieval, audio data browsing/visualization, character and pattern recognition, etc., can solve the problem of inaccurate audio summary description

Active Publication Date: 2022-07-08
AISPEECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The inventor found in the process of implementing the application that the generated audio abstract descriptions are often inaccurate, especially the description of sound events and acoustic scenes

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
  • Automatic audio summary generation method and device
  • Automatic audio summary generation method and device
  • Automatic audio summary generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Please refer to figure 1 , which shows a flowchart of an automatic audio summary generation method.

[0018] like figure 1 As shown, in step 101, a sound event detection model is pre-trained, wherein the sound event detection model includes an audio feature extraction part and an output part;

[0019] In step 102, the audi...

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 automatic audio summary generation method and device, wherein an automatic audio summary generation method includes: a pre-trained sound event detection model, wherein the sound event detection model includes an audio feature extraction part and an output part; The audio feature extraction part acts as an audio encoder for the automatic audio summary generation model; the automatic audio summary generation model is trained end-to-end. The solution of the embodiment of the present application obtains a better audio encoder through pre-training and transfer learning on the sound event detection task, so as to generate a more accurate audio summary description, and then can generate a corresponding text description for any new audio, automatically An audio-text database is established, which can support practical applications like audio retrieval engines based on unrestricted forms of natural language.

Description

technical field [0001] The invention belongs to the technical field of audio summaries, and in particular relates to an automatic audio summary generation method and device. Background technique [0002] In the related art, Automated Audio Captioning (AAC) aims to generate summary descriptions of audio clips. Many concepts are described in audio summaries, ranging from local information such as sound events to global information such as acoustic scenes. Currently, the mainstream approach to AAC is an end-to-end encoder-decoder structure, where it is hoped that the encoder can automatically learn all concepts embedded in the audio. [0003] The task of automatic audio summarization generation can be based on a piece of input audio, an encoder encodes the audio into a series of vectors, and then a decoder decodes the encoded vectors into natural language summaries. During the process of realizing the present application, the inventors found that the generated audio summary d...

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): G06F16/64G06F16/683G06K9/62
CPCG06F16/64G06F16/683G06F18/214
Inventor 俞凯吴梦玥徐薛楠丁翰林谢泽宇
Owner AISPEECH 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

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