Bone conduction speech enhancement method based on differential operation and joint dictionary learning

Abstract

The invention provides a bone conduction speech enhancement method based on differential operation and joint dictionary learning. In the training stage, in an indoor noise-free environment, a double-microphone array composed of bone conduction microphones and air conduction microphones is used for synchronously collecting training voices; short-time Fourier transform is performed on training signals of the bone conduction speech and the air conduction speech to obtain time-frequency spectrum amplitudes, and differential time-frequency spectrum amplitudes of the time-frequency spectrum amplitudes are calculated; and a joint speech dictionary of the bone conduction speech time-frequency spectrum amplitude and the differential time-frequency spectrum amplitude is learned on the time-frequencyspectrum. And at a detection stage, short-time Fourier transform is performed on the bone conduction speech to obtain a time-frequency spectrum amplitude and a phase, the is projected amplitude on abone conduction speech sub-dictionary of the joint speech dictionary, and a differential speech time-frequency spectrum amplitude is reconstructed by using an obtained optimal sparse representation coefficient and a differential time-frequency spectrum amplitude sub-dictionary of the joint speech dictionary. A bone conduction voice time-frequency spectrum is compensated and finally short-time inverse Fourier transform is performed to obtain an enhanced bone conduction voice time-domain signal.

Description

technical field [0001] The invention relates to the field of single-channel speech enhancement, in particular to a bone conduction speech enhancement method based on differential operation and joint dictionary learning. Background technique [0002] Voice plays a leading role in people's communication activities. Due to the pollution of environmental noise, the human ear and related smart devices including air conduction microphones (referred to as air conduction microphones) receive noisy voice, and the quality and intelligibility of voice will be significantly reduced, which affects people's subjective Auditory experience and speech recognition rate of smart devices. Speech enhancement technology is the main method to solve this kind of problems. How to restore clean speech from noisy speech has always been a problem that people are trying to solve. The voice received by the air conduction microphone is called air conduction voice for short. [0003] Bone conduction mi...

AI Technical Summary

Problems solved by technology

However, due to factors such as the low-pass performance of human body conduction and the limitation of the sensor technology level, the speech clarity received by the bone conduction microphone is low and sounds dull.

Images