Short-time and long-time feature modeling fusion-based environmental sound recognition method and device

Abstract

The invention discloses a short-time and long-time feature modeling fusion-based environmental sound recognition method and device. According to the invention, a model cascaded fusion method is adopted, so that short-time and long-time information can be utilized in a whole identification process. According to the technical schemes of the invention, the method includes two stages. According to the first stage, pre-classification is performed on sliding windows based on short-time features and by using the modeling of the Gaussian mixture model (GMM); confidence judgment is performed on the classification results of the GMM; a result with high confidence is directly adopted as a final classification result; and when lower confidence appears, re-classification is carried out based on long-time features. According to the second stage, based on analysis on a GMM classification result confusion matrix, classes easy to be confused are found out; and a support vector machine (SVM) classification model between the classes is trained; and re-classification is carried out by using a support vector machine (SVM). The probability score of the Gaussian mixture model used in the modeling process of the second stage is added to the long-time features, so that the probability score and the long-time features are together adopted as the input of the SVM.

Description

technical field [0001] The invention relates to the field of environmental sound recognition, in particular to the field of acoustic modeling of environmental sound. Background technique [0002] In recent years, research on non-speech perception has gradually become a research hotspot. Non-speech environmental sounds can also convey useful information, such as human activities in a specific environment usually produce a variety of acoustic events. Through the analysis and processing of these environmental sounds, people's activities and corresponding environmental conditions can be effectively learned, such as applause, laughter, footsteps, gunshots, explosions, glass shattering, etc. [0003] For environmental sound recognition, researchers have tried various methods. Since it is all about sound processing, environmental sound recognition first draws on the GMM (GaussianMixtureModel: Mixed Gaussian Model) / HMM (HiddenMarkovModel: Hidden Markov Model) technology in the fie...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the situation of insufficient i

Images