透過您的圖書館登入
IP:18.116.42.208
  • 會議論文

獨立成分分析結合子空間語音增強法於時域音訊分離之分析探討

An Audio Signal Seperation Processing Based on TD-FastICA and Subspace Signal Enhance

摘要


本研究利用獨立成分分析法,對盲訊號進行訊號分離,以解決「雞尾酒會問題」。此方法利用多支麥克風分別在不同位置接收多個不同聲源的混和訊號,將各麥克風所接收到的訊號資料點視為矩陣中的一個行,並假設這些聲源的訊號資料點皆為相互獨立的關係,便可以利用非高斯分布性質的程度來設定判斷基準並透過迭代演算法進行矩陣運算,找到將聲源訊號混和的混和矩陣之反矩陣進行解混和,得到訊號分離的結果。但是此方法在時域運算上會因不同音源到麥克風的造成時間延遲的情況,使得分離結果不佳。本研究先對訊號進行時間上位移,解決時間延遲,使獨立成分分析法在時域中能夠運行,再以子空間語音增強法進行結果優化,以達成快速與明顯的分離結果。

並列摘要


Independent Component Analysis(ICA) is the common algorithm to solve blind source separation problem(BSS). Theoretically, ICA can separate each voice which is made by different source from measured signals. However, using time domain ICA algorithm will cause time delay difference problem because the distance between the signal source and each sensor is different. Even though we can transform measured signals into frequency-domain by FFT and avoid the problem, the ambiguities of ICA will cause dilation problem and permutation problem. The topic of paper is adding pre-processing step for solving and time delay difference problem. In addition, we use subspace speech enhance as post-processing to optimize ICA result.

延伸閱讀