A method and device for audio segmentation

Abstract

The embodiment of the invention discloses an audio segmentation method and a device, and the method comprises the steps: target characteristic value of target audio can be extracted according to a preset characteristic extraction algorithm; according to the target characteristic value, the target audio is segmented into a target voice part and a target mute part; the target characteristic value serves as an input parameter of a preset Gaussian model, and a posterior probability for the target audio can be obtained; according to the posterior probability and a preset classification model, the target voice part is segmented, a target music part and a non-target music part are obtained, wherein the preset classification model is a classification model based on multi-characteristic fusion and context association; according to the target mute part, the target music part and the non-target music part generate a segmentation result for the target audio. According to the invention, the audio can be segmented into a mute part, a music part and a non-music part.

Description

technical field [0001] The present invention relates to the field of audio processing, in particular to an audio segmentation method and device. Background technique [0002] With the continuous development of Internet technology, multimedia data such as images, videos, and audios have gradually become the main forms of information media in the field of Internet information processing. Among them, audio data occupies a very important position. The raw audio data itself is a non-semantic symbolic representation and unstructured binary stream, which lacks content semantic description and structured organization. Audio segmentation technology is an important means of extracting structured information and semantic content in audio, and it is the basis for understanding, analysis and retrieval of audio and video content. Essentially, audio classification is a pattern recognition problem that includes two basic processes: feature extraction and classification. Audio segmentatio...

AI Technical Summary

Problems solved by technology

[0003] At present, the traditional audio segmentation method generally extracts the Mel cepstral coefficient features of the target audio first, and then divides the audio into speech parts and silent parts according to the Mel cepstral coefficient features and the preset mixed Gaussian classification model. The traditional method can realize the basic division of audio. However, the content of the voice part in practical applications is rich and colorful. For example, there are complex and changeable audio signals in the broadcast audio stream. Therefore, only the voice part and the Silent parts, do not take advantage of the structural information and semantic content in the extracted audio

Images