Audio characteristic classification method based on variable duration

Abstract

The invention discloses an audio characteristic classification method based on variable duration in a multimedia signal processing and mode identification technology field. The method comprises the following steps: taking a marked audio sequence whose type is determined as a training sequence; extracting short time characteristics of an audio signal in the training sequence so as to form a short time characteristic vector; calculating a statistical parameter of the each short time characteristic in setting duration so as to acquire a statistical characteristic vector corresponding to the short time characteristic vector; calculating a group of the statistical characteristic vectors corresponding to the short time characteristic vector, and forming a long time characteristic vector of the training sequence by the group of the statistical characteristic vectors; using the long time characteristic vector of the training sequence to train a classifier; extracting a short time characteristic of an ist frame audio signal in a test sequence and calculating an ist frame input long time characteristic vector of the test sequence; sending the ist frame input long time characteristic vector into the trained classifier so as to obtain a classification type. By using the method of the invention, a time-delay problem caused by long time characteristic extraction can be avoided and real time classification of the audio characteristic can be realized.

Description

technical field [0001] The invention belongs to the technical field of multimedia signal processing and pattern recognition, and in particular relates to a variable duration-based audio feature classification method. Background technique [0002] With the continuous development of communication technology, digital audio processing has been widely used in many fields such as mobile communication, Internet, broadcasting and personal electronics. From the perspective of audio codec technology, it has gradually expanded from the traditional narrowband speech-based speech coding to multimedia audio coding with higher bandwidth expansion and quality. There are higher requirements for channel adaptability, transmission reliability, and codec quality. Regardless of audio codec or sound effect editing and production, the diversity of the audio signal itself makes it possible to select different processing techniques for different types of audio signals. For example, G.718 and G.729...

AI Technical Summary

Problems solved by technology

Due to the short-term stationarity of audio signals, long-term features are generally more stable and distinguishable than short-term features, but the disadvantage is that the detection delay is large, which has certain limitations for real-time classification systems.

In addition, the stable periods exhibited by different features may be inconsistent, and it may not be optimal to calculate the corresponding long-term features under the same time length for these features

Images