Single-channel sound separation method based on human voice model

Abstract

The invention relates to a method for separating sound of single channels on the basis of human sound models. The method includes steps of building the human sound models by the aid of source filters; providing input signals; constructing human sound power of the input signals by the aid of vocal cord vibration power models and filter models of vocal tracts and oral cavities; constructing background sound power of the input signals; reconstructing signal power spectra of the input signals according to the constructed human sound power and the constructed background sound power; solving human sound power and background sound power in the reconstructed signal power spectra and separating human sound signals and background sound signals from the input signals according to the solved human sound signals and the solved background sound signals. The built human sound models comprise the vocal cord vibration power models and the filter models of the vocal tracts and the oral cavities. The method for separating the sound of the single channels has the advantages that human sound can be separated from background sound by the aid of the method under extremely noisy conditions, and the method can be used in the fields of speech enhancement, human sound extraction and the like and is high in practicality.

Description

technical field [0001] The invention relates to the technical field of sound separation, in particular to a single-channel sound separation method based on a human voice model. Background technique [0002] Speech and noise separation (Speech and noise separation) is the processing of noisy speech in order to separate the target speech in a complex noise environment. The main goal is to eliminate the interference of environmental noise on speech and improve speech quality. Speech-to-noise separation can be said to be an extension of the Speech Enhancement algorithm, and the noise it processes can even include the voices of other speakers. [0003] With the continuous development of computer signal processing technology and Internet technology, people pay more and more attention to single-channel sound separation technology, which can be used in speech enhancement, human voice extraction and other fields. This single-channel sound separation technology will be used in many c...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the defects of the prior art, provide a single-channel sound separation method based on the human voice model, and solve the performance problem that the existing separation technology cannot reach the human ear system

Images