基于小波變換和獨(dú)立分量分析的含噪混疊語(yǔ)音盲分離
Blind Separation of Noisy Speech Mixtures Based on Wavelet Transform and Independent Component Analysis
-
摘要: 含噪混疊語(yǔ)音的分離是語(yǔ)音信號(hào)處理中的重要研究問(wèn)題。該文針對(duì)語(yǔ)音信號(hào)的非平穩(wěn)特性與不同語(yǔ)音源之間的相互獨(dú)立性，提出用小波變換與獨(dú)立分量分析相結(jié)合的方法來(lái)進(jìn)行分離。首先利用小波變換分別對(duì)各含噪混疊語(yǔ)音進(jìn)行消噪，然后用獨(dú)立分量分析的方法對(duì)消噪后的混疊信號(hào)進(jìn)行分離，最后進(jìn)一步對(duì)分離信號(hào)作矢量歸一和再消噪處理，得到各個(gè)語(yǔ)音源信號(hào)的最終估計(jì)。仿真結(jié)果表明這種方法取得了很好的分離效果。
-
關(guān)鍵詞:
- 語(yǔ)音分離;小波變換;獨(dú)立分量分析;噪聲消除
Abstract: A vital issue in speech processing is to extract source speeches from noisy mixtures. A method is presented based on wavelet transform and independent component analysis in this paper. Firstly, de-noise the noisy mixtures with discrete wavelet transform. Secondly, get them separated by independent component analysis. Finally, do the post-processing to the separated signals, then the estimated source speeches are got. Simulation results exhibit a high level of separating performance. -
計(jì)量
- 文章訪問(wèn)數(shù): 2245
- HTML全文瀏覽量: 91
- PDF下載量: 1299
- 被引次數(shù): 0
下載:
