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

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...

Images