Microphone array speech enhancement method for rear FastICA signal separation

Abstract

The invention discloses a microphone array speech enhancement method based on rear FastICA signal separation. The method comprises the steps that microphone array element receiving signals are acquired and preprocessed; a fixed beam former of a upper branch performs primary noise reduction on the microphone array element receiving signal; an adaptive blocking matrix of a lower branch filters a desired signal, and an adaptive canceller outputs multiple paths of noise signals as one path of noise signal; and a FastICA algorithm is performed on the output signals of the upper and lower branch adaptive cancellers to separate voice and noise, and an enhanced voice signal in the separated signals is obtained. According to the method, leakage of target signals can be reduced, the signal-to-noise ratio of voice can be improved and enhanced, and especially when the signal-to-noise ratio of background noise Gaussian white noise is too low, the method can show excellent denoising performance and is higher in robustness.

Description

technical field [0001] The invention belongs to the technical field of electronic communication, and in particular relates to a microphone array voice enhancement method with rear FastICA signal separation. Background technique [0002] Speech signal processing has high requirements on the quality of speech. However, whether it is to transmit information to others through speech or to perform human-computer interaction with artificial intelligence products, speech will inevitably be affected by environmental noise or internal machine systems during the transmission process. The noise is polluted or even drowned out, resulting in a serious decline in speech intelligibility and intelligibility. Therefore, it must be solved by using speech enhancement technology. [0003] The purpose of speech enhancement is to extract the original speech with higher clarity and intelligibility from the speech signal polluted by interference and noise, so as to improve the quality of the speec...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a microphone array voice enhancement method for post-FastICA signal separation in view of the above-mentioned deficiencies in the prior art. The adaptive blocking matrix is ​​used to replace the traditional fixed blocking matrix, which can effectively reduce the Leakage of the target signal caused by the unknown direction, combined with the Fast Independent Component Analysis (FastICA) algorithm at the output of the GSC to further separate the pure speech and incoherent noise in the output signal, which can effectively remove noisy speech in the Gaussian white noise background When the signal-to-noise ratio of the input background noise is low, the denoising performance is more obvious, which solves the problem that the existing generalized sidelobe canceller has poor ability to eliminate incoherent noise and the blocking matrix often leaks the desired signal.

Images