A method and device for accompaniment of songs based on mmse

Abstract

The invention discloses a song accompaniment removing method based on MMSE (minimum mean-square error). The method comprises the following steps: a song audio signal and a corresponding accompaniment audio signal are input; framing, windowing and FFT transform are carried out on the song audio signal and the accompaniment audio signal; the amplitude spectrum of the accompaniment audio signal is enhanced; and MMSE estimation is performed on the spectrum of the song audio signal according to the amplitude spectrum of the enhanced accompaniment audio signal to obtain a spectrum gain coefficient, the spectrum of an accompaniment-removed audio signal is obtained, and FFT inverse transform is carried out to obtain the accompaniment-removed audio signal. The invention further provides a device for implementing the method. The method and the device of the invention have the following beneficial effects: human voice signals can be effectively extracted from songs, good sound quality can be maintained, a good foundation is laid for further analysis and retrieval of audio data, and the method and the device have high practical values and good application prospects.

Description

technical field [0001] The invention relates to the field of audio signal processing Background technique [0002] The singing voice separation system has a wide range of applications in some fields, such as the automatic recognition and correction of lyrics, which needs to be based on the previous vocal separation. Automatic lyrics recognition usually requires the input processing system to be a separate human voice, which is difficult to complete when there is interference from the accompaniment, but because most songs contain both singing voice and instrumental accompaniment, it is not practical to do it directly. [0003] In the problem of separating sounds from different sources, such a task is easy for humans but difficult for machines. Speech separation has been extensively studied, but since music is an extremely complex signal, multiple signals including singing voices and different musical instruments are mixed together, and the sound of musical instruments and si...

AI Technical Summary

Problems solved by technology

Automatic lyrics recognition usually requires the input processing system is a separate human voice, which is difficult to complete when there is interference from the accompaniment, but because most songs contain both vocal and instrumental accompaniment, it is not practical to do it directly

[0003] In the problem of separating sounds from different sources, such a task is easy for humans but difficult for machines

Speech separation has been widely studied, but since music is an extremely complex signal, multiple signals including singing and different musical instruments are mixed together, and the sound of musical instruments and singing are still related, it is difficult to separate them using blind separation technology of speech signals sing pure

Images