Environmental sound classification analysis method and device and medium

Abstract

The invention discloses an environmental sound classification analysis method and device and a medium. The method comprises the steps of performing data enhancement on voice training data; carrying out data preprocessing and carrying out feature extraction on the environment sound to obtain a feature vector; and carrying out model training on the feature vector by adopting a deep CNN network to obtain a multi-classification model of the environmental sound and outputting the multi-classification model. The data enhancement method is adopted, experiments show that the training effect is greatly improved compared with that without data enhancement, and the practical value of the system is improved.

Description

technical field

[0001] The present application relates to the field of sound classification, in particular to an environmental sound classification and analysis method, device and medium. Background technique

[0002] The use of ambient sound classification tasks can be applied to classifying different musical instruments, robotic navigation, medical or medical issues, customer or buyer reminders, crime alert systems, voice activity recognition, audio-based disaster recognition, environmental monitoring, and more. Sound classification can be involved in many applications, which shows its importance. The classification of sounds is to identify the sound categories of small audio clips or recordings. The received information derived from the audio signal is analyzed in detail. It is important to be aware of the surrounding sound environment and take immediate action to reduce risk.

[0003] The environmental sound classification technology adopted in the related art is most...

Images