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

Speech recognition method and device based on self-attention mechanism and memory network

A technology of attention and mechanism, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as low efficiency and poor speech recognition effect, increase accuracy, improve modeling ability and recognition effect, speed up training and The effect of inference speed

Active Publication Date: 2021-04-02
PING AN TECH (SHENZHEN) CO LTD
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, this application provides a speech recognition method and device based on self-attention mechanism and memory network, which mainly solves the limitations of the existing models in terms of computational complexity and accuracy when performing speech recognition. Sexuality, resulting in poor voice recognition and low efficiency

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
  • Speech recognition method and device based on self-attention mechanism and memory network
  • Speech recognition method and device based on self-attention mechanism and memory network
  • Speech recognition method and device based on self-attention mechanism and memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Hereinafter, the present application will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict.

[0024] Aiming at the problems that the existing models have certain limitations in computational complexity and accuracy during speech recognition, resulting in poor speech recognition effect and low efficiency, the embodiments of the present application provide a self-attention-based force mechanisms and memory networks for speech recognition methods such as figure 1 As shown, the method includes:

[0025] 101. Update the encoder structure and decoder structure of the RNN-Transducer model according to the self-attention mechanism and the memory network LSTM.

[0026] In this application, by combining the self-attention mechanism with the RNN-Transducer model...

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 a speech recognition method and device based on a self-attention mechanism and a memory network, relates to the technical field of artificial intelligence, and can solve the problems of poor speech recognition effect and low efficiency caused by certain limitations of an existing model in calculation complexity and accuracy during speech recognition at present. The method comprises the following steps: updating an encoder structure and a decoder structure of an RNN-Transducer model according to the self-attention mechanism and the memory network LSTM; extracting voice sequence features and text sequence features of the target voice; and determining a target text label corresponding to the target voice based on the voice sequence features and the text sequence features by using the updated RNN-Transducer model. The method is suitable for online voice recognition, for example, the method can be applied to scenes such as dialogue robots, online education and real-time conference systems.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a method and device for speech recognition based on a self-attention mechanism and a memory network. Background technique [0002] In recent years, speech recognition models with Self-Attention have attracted more and more attention. Compared with the traditional recurrent neural network model (RNN), the self-attention mechanism model has the advantages of high parallelism training and low latency. However, for real-time speech recognition models, the self-attention mechanism model has a very challenging problem, as the length of speech increases, the computational complexity of the self-attention mechanism model will increase synchronously. To solve this problem, the usual practice is to limit the receptive field of self-attention to a fixed window length. This approach can ensure the computational timeliness of the model, but it will affect the ...

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): G10L15/16G10L15/26G10L19/16
CPCG10L15/16G10L15/26G10L19/16
Inventor 罗剑王健宗程宁
Owner PING AN TECH (SHENZHEN) 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