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

Audio abstract model training method and system, electronic equipment and storage medium

A model training and audio technology, applied in audio data retrieval, neural learning methods, biological neural network models, etc., can solve problems such as the decline of abstract accuracy

Pending Publication Date: 2022-04-12
AISPEECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The drop in summarization accuracy from diversity improvements is especially pronounced for work that promotes diversity in ensembles, such as GAN-based methods

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 model training method and system, electronic equipment and storage medium
  • Audio abstract model training method and system, electronic equipment and storage medium
  • Audio abstract model training method and system, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the purpose, 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 in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0021] Please refer to figure 1 , which shows a flowchart of an embodiment of the audio summarization model training method and system of the present application.

[0022] Such as figure 1 As shown, in step 101, a discriminator and an audio summary model are trained at the same time, wherein the discriminator is used to discriminate the audio su...

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 abstract model training method and system, an electronic device and a storage medium, and the audio abstract model training method comprises the steps: training a discriminator and an audio abstract model at the same time, the discriminator being used for discriminating an audio abstract output by the audio abstract model and annotation characters to obtain a condition c, wherein the condition c is used for representing the similarity between the audio abstract and the annotated text; and adversarial training is carried out on the discriminator and the audio abstract model, so that the audio abstract model can output an audio abstract of a given condition. According to the method, the discriminator for the style of the output text and the audio abstract model are trained at the same time, the audio abstract model can be forced to output the abstract of the given condition through adversarial learning, and then the abstract of the given condition can be output by collecting the tagged text with more changeable styles. And controllable, accurate and diversified audio abstract generation is realized.

Description

technical field [0001] The invention belongs to the technical field of audio abstract model training, and in particular relates to an audio abstract model training method, system, electronic equipment and storage medium. Background technique [0002] Automatic audio summarization is a challenging task that requires identifying and understanding audio content and then summarizing it in natural language. A summary may include acoustic scenes, sound events, sound properties, and even high-level abstract semantic information. Compared with structured label output, audio summarization is more related to the way humans process audio and is suitable for automatic content description or intelligent human-computer interaction applications. [0003] Audio summarization has attracted a lot of attention in recent years. The researchers aimed to improve description accuracy by combining methods such as pre-training and additional input of keywords. However, like most natural language ...

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): G06F16/635G06F16/64G06F40/194G06K9/62G06N3/08
Inventor 俞凯吴梦玥徐薛楠
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