Environmental voice recognition method based on keypoint encoding and multi-pulse learning

A technology of environmental sound and recognition methods, applied in neural learning methods, speech recognition, speech analysis, etc., can solve problems such as low biological confidence and far-reaching information processing methods

Active Publication Date: 2019-04-12
TIANJIN UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the biological confidence of the above methods is relatively low, which is far from the information processing method of the human brain.

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
  • Environmental voice recognition method based on keypoint encoding and multi-pulse learning
  • Environmental voice recognition method based on keypoint encoding and multi-pulse learning
  • Environmental voice recognition method based on keypoint encoding and multi-pulse learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific experiments.

[0043] Such as figure 1 As shown, the system frame diagram based on sparse key point coding and impulse neural network involved in the present invention mainly includes the following steps:

[0044]Step 1, RWCP database preprocessing: select 10 different sounds from the RWCP database for recognition, namely bells (bells5), bottle (bottle1), buzzer (buzzer), cymbals (cymbals), horn Sound (horn), Kara (kara), metal (metal15); all audio sampling frequency is 16KHz, each audio sample is about 0.5-3 seconds long. The first 80 files of each category are selected as the experimental database, among which 40 are randomly selected as the training set and the other 40 are used as the test set. In addition, the "speech babble" noise is selected from the NOISEX'92 database to evaluate the robustness of the system. As shown in Table 1 and Table...

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 environmental voice recognition method based on keypoint encoding and multi-pulse learning. An environmental voice is dynamically and efficiently recognized by robustness through a brain-imitating information processor, and by taking an RWCP database as a processing object, the whole system is divided into three parts: data preprocessing, characteristic extraction and classifier classification. The invention provides a method of combining a pulse neural network on the basis of sparse keypoint encoding, wherein the voice is recognized by means of discrete pulses. In order to make full use of effective information in a whole time window, nerve cells are guided to learn by adopting a multi-pulse output learning algorithm and using a pulse number in a special interval.

Description

technical field [0001] The invention belongs to the technical field of brain-inspired computing and sound recognition in the new generation of information technology, and in particular relates to an environmental sound recognition method based on key point coding and multi-pulse learning. Background technique [0002] Environmental sound recognition is an important ability for individuals to quickly grasp useful information from the surrounding environment. Successful recognition can take rapid action before potential danger occurs to avoid emergencies. Given its importance, more and more researchers have paid attention to the task of robust ambient sound recognition. Similar to tasks such as speech or music recognition, sound recognition aims to automatically identify specific sounds from the environment. The difference is that the sound signal is unstructured, and the ambient sound is often accompanied by background noise. How to accurately identify a sudden sound in a re...

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): G10L15/16G10L15/06G10L15/02G10L15/20G10L15/01G06N3/08G06N3/06
CPCG06N3/061G06N3/08G10L15/01G10L15/02G10L15/063G10L15/16G10L15/20
Inventor 于强姚艳丽王龙标党建武
Owner TIANJIN UNIV
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