基于多参考信号ICA的目标语音提取方法

Target speech extraction method based on multiple reference signals ICA algorithm

为了能够在强噪声、干扰声等复杂环境下提取干净的目标语音,提高输出信号的信噪比和信干比,本文提出了一种基于多参考信号ICA算法的语音提取方案。该方法利用声源定位、波束形成和小波分解等算法结果作为参考信号,应用基于负熵的FastICA算法估计目标语音。使用麦克风阵实测语音信号的仿真实验证明,本文提出的算法能有效地抑制背景噪声和干扰声,恢复目标语音波形和语谱图。与常规波束形成和ICA算法相比较,本文的处理方法有更好的性能,输出信号的信噪比和信干比更高。

In order to improve the signal noise ratio （SNR） and signal interference ratio （SIR） of the output speech signal and extract pure target speech in the environment with strong noises and interferences, a novel target speech extraction method based on multiple reference signals independent component analysis ^（ICA） algorithm is proposed in this paper. Firstly, reference signals are acquired by source localization, beamforming and wavelet translation algorithms. Then the target speech is estimated by FastlCA algorithm based on the negative entropy combined with the reference signals. Simulations and experiments using microphone array signals demonstrated that background noises and interference speech were reduced and pure target speech waveform and spectrogram were recovered effectively. Compared to traditional beamforming and ICA algorithms, the proposed method achieved better performance such as higher SNR and SIR.