A music tempo spectrogram generation method based on matching pursuit

Abstract

The invention provides a tempogram generation method based on match pursuit and relates to the field of music information retrieval based on content. The method comprises the following steps: inputting a music signal, and generating a note onset detection function o(n) and carrying out framing on the o(n); taking a commonly-used tempo interval and converting the tempo interval into a frequency set; for each frequency in the frequency set, establishing a corresponding parent atom; carrying out shift operation on the parent atom, and generating a new atom every movement; forming all parent atomsand the new atoms into a redundant dictionary; carrying out match pursuit on each frame of the o(n) through the redundant dictionary to obtain a decomposition coefficient of each tempo; and finally,generating a tempogram of a music. The generated tempogram has the advantages of high resolution and high sparsity; and resolution of the tempo, shift granularity of the parent atoms and match pursuitcycle number can be set flexibly according to different requirements, and thus tempograms in different resolutions and different sparsities can be generated.

Description

technical field [0001] The invention relates to the field of content-based music information retrieval, in particular to a music tempo spectrogram generation method based on matching and pursuit. Background technique [0002] 1. Related concepts and application fields of the present invention [0003] The speed of music progress is the music tempo (tempo). In modern music, "beats per minute" (beats per minute, bpm for short) is usually used as a measure of speed, such as music tempo marks Indicates that the speed of the music is 120 quarter notes per minute, that is, the duration of each quarter note is 0.5 seconds, and the larger the bmp value, the faster the speed. [0004] Music speed is closely related to the beat and rhythm of music, and is one of the important characteristics of music. In the field of music information retrieval, speed estimation refers to estimating the traveling speed of music based on music content, starting from files containing music signal wav...

AI Technical Summary

Problems solved by technology

[0023] In summary, the existing technology cannot meet the speed resolution requirements of commonly used music speed, that is, some areas of the generated music speed spectrogram will be blurred

[0024] 2. The music velocity spectrogram generated by the existing technology is not good enough

[0026] For the ACF method, when the music speed exceeds 51bpm, its component coefficients are at normal precision (such as 1bpm), and the coefficients need to be calculated by interpolation method, which will inevitably lead to a decrease in sparsity

For the FT method, due to the existence of spectrum leakage and resolution problems, the sparsity of the frequency domain coefficients will obviously also decrease.

Therefore, the music velocity spectrogram generated by the existing technology is not good enough, and the energy concentration is poor.

Images